© 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. 57054
    Prev
    Next
    INDEX
    Explanations

    federal

    np_max-act-logits · gemini-2.0-flash
    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
    æĢ¥æĢ§
    -0.29
    lse
    -0.25
     loos
    -0.24
    asel
    -0.24
    yo
    -0.24
     loosen
    -0.24
     sieve
    -0.23
    让人们
    -0.23
    ToSend
    -0.23
    人éĥ½
    -0.23
    POSITIVE LOGITS
    strength
    0.28
    frog
    0.27
    \Column
    0.27
     Wilkinson
    0.27
    IDGET
    0.26
     organis
    0.26
     strength
    0.25
    åĨ³çŃĸéĥ¨ç½²
    0.25
    strate
    0.25
    ä¼ļ
    0.25
    Activations Density 0.004%

    No Known Activations