© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 73131
    Prev
    Next
    INDEX
    Explanations

    Tokens that occur at the start of a new segment/line (section headings or paragraph/line-initial words).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ViewHolder
    -0.08
     ut
    -0.07
     material
    -0.07
    一头
    -0.07
    _settings
    -0.07
    UserID
    -0.07
     formulation
    -0.06
    申
    -0.06
    MainActivity
    -0.06
    הזמנה
    -0.06
    POSITIVE LOGITS
     infamous
    0.07
    nock
    0.07
     froze
    0.07
     Chick
    0.06
    (blocks
    0.06
    asive
    0.06
    館
    0.06
    hevik
    0.06
    AVA
    0.06
     факт
    0.06
    Activations Density 0.443%

    No Known Activations