© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17171
    Prev
    Next
    INDEX
    Explanations

    common word endings or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usul
    -0.08
    _UNSUPPORTED
    -0.07
    天çĽĸ
    -0.07
    æĭ¥æľīçļĦ
    -0.06
    æĹŃæĹ¥
    -0.06
    uruhan
    -0.06
    Ł
    -0.06
     Marcel
    -0.06
    çĽ¸ä¼´
    -0.06
    uerte
    -0.06
    POSITIVE LOGITS
    ÃŃÄį
    0.08
     Trá»ĭ
    0.08
     Ofer
    0.07
    imon
    0.07
    indel
    0.07
    inton
    0.07
    ç¢į
    0.07
    ()>
    0.07
    orii
    0.07
    arg
    0.07
    Activations Density 0.108%

    No Known Activations