© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109767
    Prev
    Next
    INDEX
    Explanations

    slow news day

    np_max-act · gemini-2.0-flash

    the phrase/idiom "slow news day" or variants expressing that it's a slow news day (i.e., commentary that there's nothing important happening).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ти
    -0.07
    钰
    -0.07
     Julius
    -0.07
     Waterloo
    -0.07
    DownLatch
    -0.07
     Buch
    -0.07
    useppe
    -0.07
    .acquire
    -0.07
    isation
    -0.06
    .dequeue
    -0.06
    POSITIVE LOGITS
     suburbs
    0.07
     CAB
    0.07
     THEM
    0.07
    thinking
    0.07
    ento
    0.07
     referee
    0.06
    ;*/↵
    0.06
     overlaps
    0.06
     Ko
    0.06
    смотр
    0.06
    Activations Density 0.137%

    No Known Activations