© 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. 3448
    Prev
    Next
    INDEX
    Explanations

    qualities describing things

    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
    ossi
    -0.08
    大åIJī
    -0.07
    å·¥ä½ľçļĦå¼Ģå±ķ
    -0.07
    ówki
    -0.07
    段çļĦ
    -0.07
     ëĿĦ
    -0.07
    à¹Ħหว
    -0.07
    å°ĶèĴĻ
    -0.07
    æŀģ端
    -0.07
    _decor
    -0.06
    POSITIVE LOGITS
     enough
    0.15
    -looking
    0.13
     ×ij×Ļ×ķתר
    0.12
    æĹłæ¯ĶçļĦ
    0.11
     genug
    0.10
     Enough
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
    ä¸Ķ
    0.09
    ä¸Ķåħ·æľī
    0.09
    ä¸Ķæľī
    0.09
    Activations Density 0.680%

    No Known Activations