© 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. 27-TRANSCODER-HP
    7. 57775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    称
    -0.28
    综åIJĪ
    -0.26
    ystem
    -0.25
    ç»ĵåIJĪèµ·æĿ¥
    -0.25
    åįłæį®
    -0.25
    è¿ĻåĿĹ
    -0.25
    åįłæľī
    -0.25
    çŀŃ
    -0.25
    ä½Ļ
    -0.24
    稱
    -0.24
    POSITIVE LOGITS
    çļĦæķ°éĩı
    0.31
    rie
    0.29
    coli
    0.28
    åīįæīĢ
    0.27
    å±Ĭ
    0.27
    BSD
    0.27
    omas
    0.26
    ingu
    0.25
    oma
    0.24
    ream
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.