© 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. 97635
    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
    chemes
    -0.28
    undi
    -0.26
     TArray
    -0.25
    vendor
    -0.24
     detective
    -0.24
    emann
    -0.23
    æ±Ģ
    -0.23
    Overrides
    -0.23
    æľīæīĢä¸įåIJĮ
    -0.23
    çĽĬ
    -0.23
    POSITIVE LOGITS
    åĪĽéĢłåĬĽ
    0.28
    èĥĮåIJİçļĦ
    0.25
    ä¿Ŀæ´ģ
    0.25
    æĺİç¡®è§Ħå®ļ
    0.25
    cesso
    0.25
    èĥĮåIJİ
    0.24
    visualization
    0.24
    åħĭèݱ
    0.24
    legate
    0.23
    ä¸ĢåĪĨéĴŁ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.