© 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. 40035
    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
    类产åĵģ
    -0.31
    å¾Īæ·±
    -0.30
    ç²¹
    -0.27
    *size
    -0.27
     INTERN
    -0.26
    JsonValue
    -0.26
    recommended
    -0.25
    åĪ©çĶ¨æĤ¨çļĦ
    -0.25
     StringUtil
    -0.25
    èı½
    -0.25
    POSITIVE LOGITS
     Present
    0.32
     End
    0.31
     Cl
    0.30
     Past
    0.29
    รà¸Ńà¸ĩ
    0.28
     CI
    0.28
     M
    0.28
    æ¡Ĩæŀ¶
    0.28
     View
    0.28
     Public
    0.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.