© 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. 56946
    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
    çIJĨæĥ³çļĦ
    -0.25
     nevertheless
    -0.25
    ä»·åĢ¼
    -0.25
    帰
    -0.24
    egrator
    -0.24
    çļĦçIJĨæĥ³
    -0.24
    åľ¨ä¹İ
    -0.23
    incerely
    -0.23
    åĩºåĵģ
    -0.23
    家éķ¿ä»¬
    -0.23
    POSITIVE LOGITS
    maid
    0.29
     Anglo
    0.28
     unre
    0.26
    olle
    0.25
    bung
    0.25
    åħ¬
    0.24
    iode
    0.24
    áng
    0.24
    iat
    0.24
    fac
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.