© 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. 18-TRANSCODER-HP
    7. 88919
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ°å½¢
    -0.28
     tops
    -0.26
    stile
    -0.26
    åŁĶ
    -0.26
    æŃ¡è¿İ
    -0.23
    ç«Ļ
    -0.23
     perse
    -0.23
    _ly
    -0.23
    fox
    -0.23
    remen
    -0.23
    POSITIVE LOGITS
    [from
    0.28
    [mid
    0.26
    anted
    0.25
     redesigned
    0.24
    SID
    0.24
    iteDatabase
    0.24
    esson
    0.24
    .htm
    0.24
    æĦı
    0.24
    /from
    0.24
    Activations Density 0.936%

    No Known Activations

    This feature has no known activations.