© 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. 19-TRANSCODER-HP
    7. 9305
    Prev
    Next
    INDEX
    Explanations

    Warnings/Notes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liner
    -0.29
    emachine
    -0.27
    conde
    -0.24
     grounded
    -0.24
    bro
    -0.24
    _machine
    -0.24
     rico
    -0.24
    lop
    -0.23
    IX
    -0.23
    ä»İèĢĮ使
    -0.23
    POSITIVE LOGITS
    upported
    0.25
     Forward
    0.25
    éħĨ
    0.25
    ↵     ↵
    0.24
    Ĥ¨
    0.24
     doch
    0.24
    andler
    0.24
     {};↵↵
    0.24
    çĩĥ
    0.24
     Playboy
    0.23
    Activations Density 0.017%

    No Known Activations