© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25381
    Prev
    Next
    INDEX
    Explanations

    coding/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èĥ½åĬĽåĴĮ
    -0.13
     Raqqa
    -0.13
    anter
    -0.11
    ä¸Ģä¸ĭ
    -0.11
    ataire
    -0.11
    units
    -0.11
    /Framework
    -0.11
    esub
    -0.11
    ante
    -0.10
     presente
    -0.10
    POSITIVE LOGITS
     am
    0.14
     (
    0.14
    .
    0.14
    igner
    0.14
    ,
    0.13
    0.12
    (
    0.12
     #
    0.12
    __
    0.12
     returned
    0.12
    Activations Density 0.001%

    No Known Activations