© 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. 38724
    Prev
    Next
    INDEX
    Explanations

    non-english, code-related content

    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
    èij¬
    -0.29
     spo
    -0.27
    æѤç§į
    -0.26
     Spo
    -0.26
     midpoint
    -0.25
     sponsor
    -0.25
    ланд
    -0.25
     Contest
    -0.25
    ç«ĭ足
    -0.24
    íĻľ
    -0.24
    POSITIVE LOGITS
    rea
    0.34
    lete
    0.33
    an
    0.33
    rier
    0.31
    areas
    0.29
    rem
    0.28
    akter
    0.28
    ay
    0.28
    ren
    0.27
    adget
    0.27
    Activations Density 6.543%

    No Known Activations