© 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. 38527
    Prev
    Next
    INDEX
    Explanations

    h

    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
    å¼ĥ
    -0.27
    aida
    -0.24
    å¥ķ
    -0.24
    æĭIJ
    -0.23
    nc
    -0.23
    .RegisterType
    -0.23
    ç´¯
    -0.23
     onCreateView
    -0.22
     domestically
    -0.22
    æĬ±æĢ¨
    -0.22
    POSITIVE LOGITS
     undertaken
    0.47
     undertaking
    0.47
     undert
    0.46
     undertake
    0.37
     endeavor
    0.37
     Undert
    0.33
     endeavors
    0.32
    geois
    0.27
     endeavour
    0.27
    itches
    0.26
    Activations Density 82.180%

    No Known Activations