© 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. 88418
    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
    æĴ
    -0.29
    éŵ
    -0.29
    被æīĵ
    -0.28
     pew
    -0.28
     confused
    -0.27
    为空
    -0.27
    ç½²
    -0.26
    èł¢
    -0.26
    Royal
    -0.25
    !.↵↵
    -0.25
    POSITIVE LOGITS
    inction
    0.30
     unwind
    0.27
    .TryParse
    0.26
    ostringstream
    0.26
     consenting
    0.25
    erty
    0.25
    åĩŃè¯ģ
    0.25
    Cumh
    0.24
    FRING
    0.24
    Keeper
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.