© 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. 44214
    Prev
    Next
    INDEX
    Explanations

    code or statistic concepts

    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
    产åĵģè´¨éĩı
    -0.28
    (predictions
    -0.25
     войнÑĭ
    -0.25
    åħīè¾ī
    -0.25
    å®ĺæĸ¹å¾®åįļ
    -0.24
    å½¼
    -0.24
    壶
    -0.24
     Rodrig
    -0.24
    æīĩ
    -0.23
    èĭ±éĽĦ
    -0.23
    POSITIVE LOGITS
     option
    0.46
     requirement
    0.45
     condition
    0.44
     statistic
    0.40
     thing
    0.39
     element
    0.38
     consequence
    0.38
    	option
    0.37
     assumption
    0.37
    (option
    0.37
    Activations Density 0.003%

    No Known Activations