© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 57709
    Prev
    Next
    INDEX
    Explanations

    ore

    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_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
    _PAY
    -0.08
    ]!=
    -0.08
    ++]=
    -0.08
    <Product
    -0.08
    自己喜欢
    -0.08
    AVA
    -0.07
    -round
    -0.07
    ulos
    -0.07
    ,right
    -0.07
     imgUrl
    -0.07
    POSITIVE LOGITS
    dé
    0.08
    pub
    0.07
    othy
    0.07
     exceptional
    0.07
    ad
    0.07
     וה
    0.07
    istent
    0.06
    arent
    0.06
     不
    0.06
    🌡
    0.06
    Activations Density 0.008%

    No Known Activations