© 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. 39468
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     oversh
    -0.25
    å±ģèĤ¡
    -0.25
     {[
    -0.24
    èłĵ
    -0.24
    ocabulary
    -0.24
    ampler
    -0.23
    adir
    -0.23
    antages
    -0.23
    æīĵè´¥
    -0.23
    æľŁ
    -0.23
    POSITIVE LOGITS
    æĮĤ
    0.31
     sparing
    0.29
    krit
    0.29
    ä¸įçķĻ
    0.28
    æĬķåħ¥åĪ°
    0.27
    æ½ľ
    0.26
    åĽºåĮĸ
    0.26
     Casting
    0.26
    举
    0.26
    éģĵ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.