© 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. 88033
    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
     trade
    -0.29
    è¾Ľ
    -0.28
     Cheat
    -0.26
    .err
    -0.26
     reliance
    -0.25
     bob
    -0.24
    bob
    -0.24
    ä¸¥æł¼
    -0.24
     Bob
    -0.23
    atted
    -0.23
    POSITIVE LOGITS
    iph
    0.26
    à¹Īาà¸ĩ
    0.25
    Coins
    0.25
    é£İçŃĿ
    0.25
    upal
    0.24
    /ph
    0.24
    缸çĪ±
    0.24
    PHA
    0.23
    ç»ĿæľĽ
    0.23
    mouth
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.