© 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. 39674
    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
    æĿ¡ä»¶ä¸ĭ
    -0.28
    rien
    -0.27
    æµģç¨ĭ
    -0.26
    /Internal
    -0.26
     ([]
    -0.25
    inish
    -0.25
    äºıæįŁ
    -0.25
    éĽĨåĽ¢èĤ¡ä»½
    -0.25
    éĢĤåIJĪèĩªå·±
    -0.25
    stantiate
    -0.24
    POSITIVE LOGITS
    IFY
    0.30
     sway
    0.28
    ABI
    0.26
    combe
    0.25
     directions
    0.25
     sound
    0.25
    airs
    0.24
    .sound
    0.24
    ported
    0.24
    Buying
    0.24
    Activations Density 0.078%

    No Known Activations

    This feature has no known activations.