© 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. 58329
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å§Ĩ
    -0.26
    umo
    -0.24
    =index
    -0.24
    éģł
    -0.24
     far
    -0.23
    ä¸Ŀ
    -0.23
    lsx
    -0.23
     using
    -0.23
    åĴĮåıijå±ķ
    -0.23
     hand
    -0.23
    POSITIVE LOGITS
    ä¸ĸä¸Ĭ
    0.30
    å·®è·Ŀ
    0.28
    æĶ¾å®½
    0.27
    æķ£å¸ĥ
    0.27
    åѦåİĨ
    0.26
    æ±Łå±±
    0.26
    å¿ĥå¾Ĺ
    0.26
    RU
    0.26
    FTA
    0.25
    æĹ¥æĬ¥è®°èĢħ
    0.25
    Activations Density 0.011%

    No Known Activations