© 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. 125922
    Prev
    Next
    INDEX
    Explanations

    Experimental treatment effects

    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
    _loaded
    -0.07
    팎
    -0.06
     Russian
    -0.06
    ints
    -0.06
     suche
    -0.06
    /Graphics
    -0.06
     billions
    -0.06
    .getMax
    -0.06
    ius
    -0.06
    .Tasks
    -0.06
    POSITIVE LOGITS
    {*
    0.07
     martyr
    0.07
    (!_
    0.07
    照亮
    0.07
    😽
    0.06
    IRO
    0.06
    Single
    0.06
    VERTISE
    0.06
    erson
    0.06
    的理由
    0.06
    Activations Density 0.086%

    No Known Activations