© 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. 40061
    Prev
    Next
    INDEX
    Explanations

    the

    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
    æİĺ
    -0.28
    æľīæ¯Ĵ
    -0.26
    æľįåĬ¡äºİ
    -0.26
     berth
    -0.25
     molecular
    -0.25
    .species
    -0.25
    æĿł
    -0.25
    æµģ
    -0.25
    åıĺå½¢
    -0.25
     molecule
    -0.24
    POSITIVE LOGITS
     Jensen
    0.32
     Sachs
    0.31
     Cupertino
    0.28
     Gupta
    0.28
     Ipsum
    0.28
     Giuliani
    0.27
     Fayette
    0.27
     Scotia
    0.27
     Dayton
    0.27
     Abrams
    0.27
    Activations Density 2.597%

    No Known Activations