© 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. 98057
    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
    /books
    -0.25
    ç®±åŃIJ
    -0.25
    ophone
    -0.25
    mas
    -0.24
    _OC
    -0.24
    åĪĨå¸ĥåľ¨
    -0.23
    ently
    -0.23
    ctest
    -0.23
    <td
    -0.23
    national
    -0.22
    POSITIVE LOGITS
     grown
    0.25
     singles
    0.24
    oil
    0.23
     оÑĤноÑĪении
    0.23
     sensitivity
    0.23
    single
    0.22
    *',
    0.22
    æīī
    0.22
     Samurai
    0.22
    __',
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.