© 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. 41068
    Prev
    Next
    INDEX
    Explanations

    Catholic nuns and orders

    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
     collar
    -0.27
    ç¼ĿéļĻ
    -0.26
    åĭ¢
    -0.26
    avn
    -0.25
    ings
    -0.25
    quito
    -0.24
    å¸ĤæķĻèĤ²
    -0.24
    ä¸¥æł¼çļĦ
    -0.24
    ymes
    -0.23
    éģĩä¸Ĭ
    -0.23
    POSITIVE LOGITS
     Nic
    0.29
    =output
    0.26
    agh
    0.26
     nor
    0.26
    LET
    0.25
    adians
    0.25
    NER
    0.25
    ĺ认
    0.25
    ove
    0.24
    (ro
    0.24
    Activations Density 0.002%

    No Known Activations