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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 59476
    Prev
    Next
    INDEX
    Explanations

    say "class"

    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
     Ro
    -0.07
    су
    -0.07
    Slinky
    -0.07
     Chin
    -0.07
    /cop
    -0.06
    .toast
    -0.06
    ”,
    -0.06
    "While
    -0.06
    .textField
    -0.06
     svo
    -0.06
    POSITIVE LOGITS
    -ed
    0.07
    Equ
    0.07
     averages
    0.07
    얐
    0.07
     maternity
    0.07
    _managed
    0.07
     Detected
    0.07
    Features
    0.07
    _NONNULL
    0.07
     whopping
    0.06
    Activations Density 0.001%

    No Known Activations