© 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. 8391
    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
    ä¸ĬæĬ¥
    -0.27
     pond
    -0.27
    AAF
    -0.26
    åºĶæĢ¥é¢Ħæ¡Ī
    -0.26
    اعدة
    -0.26
    yar
    -0.25
     sno
    -0.25
    endar
    -0.25
    çļĦæĥħåĨµä¸ĭ
    -0.25
    æīĺè¿IJ
    -0.24
    POSITIVE LOGITS
     organ
    0.28
    ç´ł
    0.28
    olin
    0.25
    ugin
    0.25
     Broad
    0.25
    tu
    0.25
     organizer
    0.24
    ienes
    0.24
    èķĪ
    0.24
    è§ĨåIJ¬
    0.24
    Activations Density 0.000%

    No Known Activations