© 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. 58366
    Prev
    Next
    INDEX
    Explanations

    medical or police texts

    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
    åĿIJåľ¨
    -0.47
    åĿIJä¸ĭ
    -0.46
    å±ıå¹ķ
    -0.42
    ç«Ļç«ĭ
    -0.42
     browser
    -0.41
     screen
    -0.41
     telephone
    -0.40
    æķ£æŃ¥
    -0.39
    åĿIJ
    -0.39
    å±ı
    -0.39
    POSITIVE LOGITS
    综åIJĪæ²»çIJĨ
    0.31
    ãģ«ãģĹãģ¦
    0.25
    ablo
    0.24
    uate
    0.24
    éĴĹ
    0.24
     alist
    0.23
    åªļ
    0.23
     Doll
    0.23
    形容
    0.23
    ãģ£ãģ½
    0.23
    Activations Density 0.001%

    No Known Activations