© 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. 45850
    Prev
    Next
    INDEX
    Explanations

    formal definitions and conditions

    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
    asuk
    -0.07
    æĺ¥æĻļ
    -0.07
    å¸ĥè¢ĭ
    -0.07
    çľĭçľĭåIJ§
    -0.07
    æľŁéĹ´
    -0.07
    å·¥ä½ľæĢ»ç»ĵ
    -0.07
    ight
    -0.07
    æ°´ä»Ļ
    -0.07
    assist
    -0.06
    arefa
    -0.06
    POSITIVE LOGITS
    tor
    0.08
    åĽŀå¡«
    0.07
    æĿİ家
    0.07
    åı¯äº²
    0.06
    appy
    0.06
    ENCE
    0.06
     confirming
    0.06
    IVERY
    0.06
    并ä¸įç®Ĺ
    0.06
     réalis
    0.06
    Activations Density 0.008%

    No Known Activations