© 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. 35-TRANSCODER-HP
    7. 39737
    Prev
    Next
    INDEX
    Explanations

    Numbers and Calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -office
    -0.30
    AndView
    -0.28
    -Agent
    -0.28
     licensee
    -0.28
     Toastr
    -0.27
    otech
    -0.27
    ouser
    -0.26
    eliac
    -0.26
    andex
    -0.26
    asti
    -0.26
    POSITIVE LOGITS
    ,
    0.58
    ï¼Į
    0.48
    0.44
     ,
    0.37
    py
    0.31
    ,↵
    0.30
    ØĮ
    0.30
     py
    0.30
     =
    0.29
    ÏĢ
    0.29
    Activations Density 0.034%

    No Known Activations