© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 28249
    Prev
    Next
    INDEX
    Explanations

    import ... as

    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
    å¤ļ空
    -0.08
    orpor
    -0.07
    è¦ģå¤ļ
    -0.07
    ä¸įæ²»
    -0.06
    asian
    -0.06
    èĪ
    -0.06
    åįİéĺ³
    -0.06
    è¿ijäºĨ
    -0.06
    çļĦä¸Ģç±»
    -0.06
    áŀı
    -0.06
    POSITIVE LOGITS
    velt
    0.08
    ago
    0.08
    inker
    0.08
    acles
    0.07
    essional
    0.07
    çĤ¯
    0.07
    vens
    0.07
    cope
    0.07
    SENT
    0.07
    usk
    0.07
    Activations Density 0.016%

    No Known Activations