© 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. 38548
    Prev
    Next
    INDEX
    Explanations

    n

    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
    th
    -0.35
    bsp
    -0.34
    ative
    -0.33
    oun
    -0.33
    ak
    -0.32
    tml
    -0.31
    osti
    -0.31
    ik
    -0.30
    ymi
    -0.29
    ¨
    -0.29
    POSITIVE LOGITS
    ç¨ĭ
    0.59
    ç¨ĭåºı
    0.58
     program
    0.57
     programs
    0.56
     Programs
    0.48
     programmes
    0.48
     Program
    0.47
     programme
    0.43
    ç¨ĭå¼ı
    0.41
     Programme
    0.39
    Activations Density 79.241%

    No Known Activations