© 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. 23-TRANSCODER-HP
    7. 23794
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    åºĬ
    -0.29
     figure
    -0.27
    æĴĴ
    -0.25
     ÃŃnd
    -0.25
    éĵ¡
    -0.25
     cri
    -0.24
    (tm
    -0.24
    èĤĮ
    -0.24
    æŀķ
    -0.24
     por
    -0.24
    POSITIVE LOGITS
    ÑĪим
    0.29
    /${
    0.27
    },${
    0.27
    .scope
    0.25
    _${
    0.25
    ãģĦãģĭ
    0.25
    >Last
    0.25
    sic
    0.25
    :${
    0.25
    [${
    0.24
    Activations Density 0.156%

    No Known Activations

    This feature has no known activations.