© 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. 31-TRANSCODER-HP
    7. 19892
    Prev
    Next
    INDEX
    Explanations

    Medical/virology texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pact
    -0.29
    issions
    -0.28
    ment
    -0.27
    acha
    -0.27
    bout
    -0.27
    acles
    -0.27
    ±Ð¾ÑĤ
    -0.25
    åĴİ
    -0.25
    iter
    -0.25
    ucle
    -0.25
    POSITIVE LOGITS
    éķľ
    0.35
    梯
    0.32
     mirrored
    0.30
     Mir
    0.29
    éı¡
    0.29
    Mir
    0.29
    åĽ´å¢Ļ
    0.28
    åĩĢ
    0.27
    空
    0.27
    èµĦ
    0.26
    Activations Density 0.030%

    No Known Activations