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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 85815
    Prev
    Next
    INDEX
    Explanations

    enabled

    np_max-act · gemini-2.0-flash
    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
     Españ
    -0.07
    -contact
    -0.07
    -meter
    -0.07
    rost
    -0.07
    lymp
    -0.06
    Incorrect
    -0.06
     camp
    -0.06
    -risk
    -0.06
    NSNotificationCenter
    -0.06
    ating
    -0.06
    POSITIVE LOGITS
     الولا
    0.08
    ,
    0.07
     derivative
    0.07
     worden
    0.07
    .absolute
    0.07
     GPL
    0.07
    ThreadId
    0.07
     lemma
    0.07
     promotes
    0.07
     gala
    0.07
    Activations Density 0.008%

    No Known Activations