© 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. 8490
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    series
    -0.29
    eries
    -0.29
    åį¯
    -0.28
     biting
    -0.27
    就说
    -0.27
    ux
    -0.25
    ÑģÑĤÑĢ
    -0.25
    orum
    -0.25
    ble
    -0.25
    ukan
    -0.25
    POSITIVE LOGITS
    åħ«åį¦
    0.24
    /Object
    0.24
    æĸ·
    0.23
    деÑĢжива
    0.23
    rette
    0.23
     concession
    0.23
    pmat
    0.23
     }}">{{
    0.23
    isas
    0.22
    认åı¯
    0.22
    Activations Density 0.002%

    No Known Activations