© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22169
    Prev
    Next
    INDEX
    Explanations

    fight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    yne
    -0.28
    dy
    -0.27
    ol
    -0.26
    wor
    -0.26
    å¤©åľ°
    -0.26
    dfs
    -0.25
    ợ
    -0.25
    airs
    -0.25
     cadre
    -0.25
    çļĦ大
    -0.25
    POSITIVE LOGITS
    ocz
    0.28
    (tol
    0.26
     himself
    0.26
    个æľĪåĨħ
    0.25
    typeid
    0.25
    UrlParser
    0.25
    onth
    0.24
    RenderingContext
    0.24
    ĪæĿĥ
    0.24
    éĻĨç»Ń
    0.24
    Activations Density 0.006%

    No Known Activations