© 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. 112555
    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
    赶ä¸Ĭ
    -0.29
    ane
    -0.27
    arn
    -0.27
     Barber
    -0.25
     vit
    -0.25
    ymm
    -0.25
     Ages
    -0.24
    (Method
    -0.23
     cigarettes
    -0.23
    land
    -0.23
    POSITIVE LOGITS
     Saved
    0.28
    saved
    0.27
    uç
    0.24
     @@
    0.24
    æľįåĬ¡æ°´å¹³
    0.24
     Response
    0.24
    人éĢī
    0.24
    otomy
    0.24
    æĶ¶åħ¥
    0.24
    éĶĢåĶ®æĶ¶åħ¥
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.