© 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. 32-TRANSCODER-HP
    7. 40953
    Prev
    Next
    INDEX
    Explanations

    middle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uen
    -0.36
    @Module
    -0.30
    ëĭĪëĭ¤
    -0.28
    å·¥åķĨ
    -0.26
    ấn
    -0.25
    Chapter
    -0.25
    orgen
    -0.25
    äººåľ¨
    -0.24
     Hasan
    -0.24
    allen
    -0.23
    POSITIVE LOGITS
     middle
    0.35
    middle
    0.33
    Middle
    0.30
     central
    0.28
     ä¸Ń
    0.28
    oker
    0.27
     midst
    0.27
    ä¸Ńæŀ¢
    0.27
     midd
    0.27
     midpoint
    0.27
    Activations Density 0.002%

    No Known Activations