© 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. 112408
    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
    è¯įæ±ĩ
    -0.28
    åı¥åŃIJ
    -0.27
    İ·
    -0.25
    æĬĽ
    -0.25
    enty
    -0.25
    æł¸
    -0.24
    FOR
    -0.24
    éĿĸ
    -0.24
    é««
    -0.24
    equality
    -0.24
    POSITIVE LOGITS
    heits
    0.26
     Pale
    0.26
    oubles
    0.25
    -compose
    0.23
     hải
    0.23
     commod
    0.23
    nil
    0.23
    ville
    0.23
    hya
    0.23
    emic
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.