© 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. 19-RESID-POST-AA
    11. 68615
    Prev
    Next
    INDEX
    Explanations

    these

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beh
    -0.08
    (build
    -0.07
    /perl
    -0.07
    "--
    -0.06
    */,
    -0.06
    _ber
    -0.06
     Nissan
    -0.06
    (),"
    -0.06
     ic
    -0.06
     HttpServlet
    -0.06
    POSITIVE LOGITS
    _loop
    0.08
     Group
    0.07
    多样性
    0.07
    骚扰
    0.06
    ساط
    0.06
     forState
    0.06
    一场
    0.06
    _lane
    0.06
    dato
    0.06
     largely
    0.06
    Activations Density 0.372%

    No Known Activations