© 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. 8691
    Prev
    Next
    INDEX
    Explanations

    Dates and time periods

    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
    ware
    -0.30
    antic
    -0.25
    abouts
    -0.25
     ESL
    -0.24
    鸣
    -0.24
    Balancer
    -0.24
    ,{"
    -0.24
    æĪļ
    -0.24
     Exactly
    -0.24
    ANTS
    -0.23
    POSITIVE LOGITS
    once
    0.27
     once
    0.26
     endpoints
    0.26
    åģıä½İ
    0.25
    tam
    0.25
    åıĬ缸åħ³
    0.25
    æĸ°æł¼å±Ģ
    0.23
    //----------------------------------------------------------------------------↵
    0.23
    olley
    0.23
     jade
    0.23
    Activations Density 0.024%

    No Known Activations