© 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. 141325
    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
    )(__
    -0.28
    æŁ
    -0.26
    rais
    -0.25
    annabin
    -0.24
    ARY
    -0.24
    rlen
    -0.24
    shr
    -0.24
    Åļ
    -0.24
    åħħåĪĨä½ĵçİ°
    -0.23
    utter
    -0.23
    POSITIVE LOGITS
    bil
    0.27
    DataProvider
    0.25
    .ext
    0.25
    ä¸ĢåĽ¢
    0.25
    ometer
    0.25
    åºķå±Ĥ
    0.24
    宦
    0.24
     Decomp
    0.24
    ouston
    0.24
    åı¸æľº
    0.24
    Activations Density 13.390%

    No Known Activations

    This feature has no known activations.