© 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. 39645
    Prev
    Next
    INDEX
    Explanations

    P

    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
    duction
    -0.28
    ä¹Łä¸įæĺ¯
    -0.26
     enr
    -0.25
    åĽ°
    -0.25
    pow
    -0.24
    äºĭåIJİ
    -0.24
    luet
    -0.23
    é¾Ļ头
    -0.23
    è¢«åĽ°
    -0.23
     bü
    -0.23
    POSITIVE LOGITS
     Beckham
    0.28
    elsius
    0.28
    åŃĺ
    0.26
    isko
    0.25
     Salman
    0.25
     Produkte
    0.25
     Smith
    0.24
     fark
    0.24
     personal
    0.24
     campaigned
    0.24
    Activations Density 0.578%

    No Known Activations