© 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. 87544
    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
    chè
    -0.26
    licer
    -0.25
     (!!
    -0.25
     distributions
    -0.23
    wake
    -0.23
    ymes
    -0.23
    åĸĿ
    -0.23
    ENSE
    -0.23
     instant
    -0.23
     Nim
    -0.22
    POSITIVE LOGITS
    æľ¬æĬ¥
    0.31
    æľ¬æľŁ
    0.29
    /cms
    0.28
    Cong
    0.27
    æľ¬äºº
    0.27
    ç¢Ľ
    0.25
    leh
    0.25
    hart
    0.25
    åı¦æľī
    0.24
    大éĻĨ
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.