© 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. 63884
    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
    ç½ij讯
    -0.29
    æѦ
    -0.25
    溯
    -0.24
     resale
    -0.24
    åı³æīĭ
    -0.23
    客æłĪ
    -0.23
    arus
    -0.23
    åĵ¥ä»¬
    -0.23
    æ¦ľé¦ĸ
    -0.23
    imus
    -0.22
    POSITIVE LOGITS
    bled
    0.25
    istrate
    0.24
     zb
    0.23
    ongan
    0.23
    cy
    0.23
     til
    0.23
    ANCES
    0.23
     bist
    0.23
    rio
    0.21
    omy
    0.21
    Activations Density 15.708%

    No Known Activations

    This feature has no known activations.