© 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. 39030
    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
    è¿Ļç§įæĸ¹å¼ı
    -0.27
    è·¯
    -0.27
     Sim
    -0.25
    è¾ĺ
    -0.25
    æĸ¹å¼ı
    -0.25
    Sim
    -0.25
    yme
    -0.24
    åĽ°
    -0.24
     trợ
    -0.24
    ì·¨
    -0.24
    POSITIVE LOGITS
     subclass
    0.27
    esis
    0.26
     Tmin
    0.25
    ä½İä½į
    0.25
    æĬ½
    0.25
     positioned
    0.24
     valued
    0.24
    å¿ħä¸įåı¯
    0.24
     gad
    0.24
    ç¼İ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.