© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6967
    Prev
    Next
    INDEX
    Explanations

    Actions and processes

    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
    .setLevel
    -0.29
    å¼¹
    -0.27
     quits
    -0.26
    ->__
    -0.25
    éĢļåħ³
    -0.24
    æĪ·å¤ĸ
    -0.24
    bö
    -0.24
     rien
    -0.24
    omen
    -0.23
    mdat
    -0.23
    POSITIVE LOGITS
    Ļ¨
    0.27
    FFF
    0.27
    é«ĺåĩº
    0.26
    ä¸įå°ij人
    0.25
    ÑģÑĤи
    0.25
    rap
    0.25
    IFY
    0.25
     *[
    0.24
    croll
    0.24
     dép
    0.24
    Activations Density 0.028%

    No Known Activations