© 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. 27-TRANSCODER-HP
    7. 9660
    Prev
    Next
    INDEX
    Explanations

    medical/cancer topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ework
    -0.26
    zie
    -0.25
     Jennings
    -0.25
    åŃIJå¼¹
    -0.24
    eso
    -0.24
     Tutor
    -0.24
    _tcp
    -0.24
    æĿŁ
    -0.24
    istle
    -0.23
    .Framework
    -0.23
    POSITIVE LOGITS
    å¹½
    0.29
    æ´»è·ĥ
    0.25
    inja
    0.25
    -validation
    0.25
    æĢĢ
    0.25
    lain
    0.25
    activated
    0.25
    æŃ£å¼ı
    0.24
     infection
    0.24
    åĽŁ
    0.24
    Activations Density 0.069%

    No Known Activations