© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    Barr

    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
     çift
    -0.28
     back
    -0.28
    orie
    -0.27
     double
    -0.27
    Ñĥма
    -0.26
     single
    -0.25
     symbol
    -0.25
     pairing
    -0.25
    æģ¢
    -0.25
    ä¸ĸéĹ´
    -0.25
    POSITIVE LOGITS
    åłĤ
    0.28
     projectName
    0.28
     CALLBACK
    0.28
     dém
    0.27
    ROOM
    0.26
    yclopedia
    0.26
    ä¸į足以
    0.25
    /editor
    0.25
     barric
    0.25
    room
    0.25
    Activations Density 0.031%

    No Known Activations