© 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. 17730
    Prev
    Next
    INDEX
    Explanations

    Profit/Non-profit

    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
     champs
    -0.09
     Республик
    -0.08
    墀
    -0.08
    ��
    -0.07
    etes
    -0.07
    ʯ
    -0.07
    (Tree
    -0.07
    ADMIN
    -0.07
    indow
    -0.07
    ultimate
    -0.07
    POSITIVE LOGITS
    _don
    0.08
    Linear
    0.07
    约为
    0.07
    文化创意
    0.07
    Children
    0.07
    _collect
    0.07
    _cos
    0.07
     varying
    0.07
    不少
    0.07
     fun
    0.07
    Activations Density 0.073%

    No Known Activations