© 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. 22-TRANSCODER-HP
    7. 130543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spl
    -0.23
     Brunswick
    -0.23
    аÑĢÑĤ
    -0.23
    illard
    -0.22
    dux
    -0.22
    åľ¨çݩ家
    -0.22
    atas
    -0.22
    !--
    -0.22
    endra
    -0.21
     bol
    -0.21
    POSITIVE LOGITS
    ç´¢
    0.26
    isce
    0.23
    ç³ł
    0.22
    ensor
    0.22
    uce
    0.22
    upport
    0.21
    ç³»åĪĹ
    0.21
    пал
    0.21
    .define
    0.21
    讹
    0.21
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.