© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38535
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    Ø£ÙĪضاع
    -0.48
    ÙħراÙĥ
    -0.46
    ÙħÙģاÙĪضات
    -0.45
    ÙħدÙĬرÙĬØ©
    -0.43
    Ùħغرب
    -0.43
    ÙħصÙĦØŃØ©
    -0.42
    أغÙĦب
    -0.42
    ÙħصاÙĦØŃ
    -0.42
    اÙĦطائÙģ
    -0.40
    تخطÙĬØ·
    -0.40
    POSITIVE LOGITS
    اÙĦ
    0.33
    ا
    0.32
    ر
    0.31
    Ø°
    0.31
     Legend
    0.30
    ÙĪر
    0.29
    ÙIJ
    0.29
    س
    0.29
    ÙĨ
    0.29
    ÙĨس
    0.29
    Activations Density 5.489%

    No Known Activations