© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    navigate

    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
    reetings
    -0.28
    éĽĦåİļ
    -0.27
    orem
    -0.24
    åĽ½åĬ¡
    -0.24
     Worldwide
    -0.24
    loys
    -0.24
    uzu
    -0.23
    oss
    -0.23
    tier
    -0.23
    èĥļ
    -0.23
    POSITIVE LOGITS
     organ
    0.27
    icular
    0.26
    hex
    0.25
    поÑĤ
    0.24
    ella
    0.24
    ration
    0.24
    atorial
    0.23
    /filter
    0.23
     closely
    0.23
    èĥ½åĬĽ
    0.23
    Activations Density 2.160%

    No Known Activations