© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7900
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    èĢĮåIJİ
    -0.27
    ieres
    -0.27
     reopened
    -0.26
     tofu
    -0.25
     respawn
    -0.23
    çĸı
    -0.23
    caled
    -0.23
     swe
    -0.23
    ORE
    -0.23
    гиб
    -0.23
    POSITIVE LOGITS
    åĽ½å®¶æłĩåĩĨ
    0.29
    killer
    0.27
    groups
    0.27
    Groups
    0.26
    çĶµç«Ļ
    0.26
    Iterations
    0.25
     diarr
    0.25
     prelim
    0.25
    elsius
    0.25
    ä¸ªåĽ½å®¶
    0.25
    Activations Density 0.015%

    No Known Activations