© 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. 129576
    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
    使çĶ¨èĢħæĪĸ
    -0.25
     bumper
    -0.23
    年人
    -0.23
    orum
    -0.23
    .|
    -0.23
    å°ıç¨ĭåºı
    -0.22
     +=↵
    -0.22
    æľ¬æĬ¥
    -0.22
    ãģķãĤī
    -0.22
    nek
    -0.22
    POSITIVE LOGITS
     mies
    0.25
    atu
    0.24
    ãģĹãĤĩãģĨ
    0.23
    ç³ł
    0.23
     **
    0.23
    _CID
    0.23
    ASTER
    0.23
    åĪĹåĩº
    0.23
    æĺ¯æĪij们
    0.23
    éĩįä¸Ńä¹ĭéĩį
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.