© 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. 58523
    Prev
    Next
    INDEX
    Explanations

    Punctuation (dot)

    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
     Cook
    -0.26
    ateur
    -0.24
    ility
    -0.24
    åīįçŀ»æĢ§
    -0.24
    ACITY
    -0.24
    ä¸ĭåĪĹ
    -0.24
    æĹħ游æĻ¯åĮº
    -0.23
    éľĩæĴ¼
    -0.23
    åİŁåĽł
    -0.23
    èµŀèµı
    -0.23
    POSITIVE LOGITS
    ystone
    0.29
    åĮħåĽ´
    0.28
    ystick
    0.27
     erection
    0.26
    åĮ£
    0.26
    ermann
    0.26
     spur
    0.25
    为ä¸Ģä½ĵçļĦ
    0.24
    leanup
    0.24
    éĻ¤æѤ
    0.24
    Activations Density 0.002%

    No Known Activations