© 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. 40237
    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
    <|endoftext|>
    -0.37
    åģļ
    -0.32
    æĿ¡
    -0.31
    éĢļè¿ĩ
    -0.30
    ,"
    -0.29
    5
    -0.29
    ç²¾ç¥ŀ
    -0.29
    "
    -0.29
    ↵↵
    -0.29
    å¸Ń
    -0.29
    POSITIVE LOGITS
    startup
    0.30
    ennon
    0.29
    RetVal
    0.28
     unregister
    0.25
    -contrib
    0.25
    EntryPoint
    0.24
     giriÅŁ
    0.24
    家åĸ»æĪ·
    0.24
    .unregister
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    Activations Density 0.025%

    No Known Activations

    This feature has no known activations.