© 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. 20-TRANSCODER-HP
    7. 107657
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿Ŀå®Ī
    -0.27
    ,std
    -0.27
    éķĩæĶ¿åºľ
    -0.25
    åĪĨ级
    -0.24
    éĥ¨ä¸»ä»»
    -0.24
    åħĭæĭī
    -0.24
    ç±³ç²ī
    -0.23
    éĿ¢ä¸Ĭ
    -0.23
    CTYPE
    -0.23
    Friendly
    -0.23
    POSITIVE LOGITS
    令
    0.35
    vs
    0.26
    åħį
    0.26
    ’
    0.25
     EXPORT
    0.24
    伸
    0.23
    see
    0.23
    SIGN
    0.23
    gien
    0.23
    /***/
    0.23
    Activations Density 63.851%

    No Known Activations

    This feature has no known activations.