© 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. 39647
    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
    iks
    -0.26
    irms
    -0.26
    Ñīий
    -0.25
    缸åIJĮçļĦ
    -0.25
    绣ä¸Ģ
    -0.24
     siblings
    -0.24
    åĿĩ为
    -0.24
    ç¯ĩç«ł
    -0.24
    æ³¢åĬ¨
    -0.23
    orie
    -0.23
    POSITIVE LOGITS
     **
    0.24
     fat
    0.24
     PURPOSE
    0.23
     deeply
    0.23
     persist
    0.23
    XMLElement
    0.23
     highly
    0.23
     Paren
    0.23
     profile
    0.23
    èĵ¼
    0.23
    Activations Density 0.392%

    No Known Activations

    This feature has no known activations.