Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 2974
    Prev
    Next
    INDEX
    Explanations

    open square bracket

    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
     One
    -0.07
     footsteps
    -0.07
     sollen
    -0.06
    _remote
    -0.06
    /sites
    -0.06
    .Business
    -0.06
    inceton
    -0.06
    _frontend
    -0.06
    悄悄
    -0.06
    _EX
    -0.06
    POSITIVE LOGITS
     mục
    0.07
    功率
    0.07
    ;';↵
    0.07
     pelvic
    0.07
    iteral
    0.07
     двигател
    0.07
     Peanut
    0.07
    [
    0.06
     cach
    0.06
    ,array
    0.06
    Activations Density 0.020%

    No Known Activations