© 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. 43316
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters or symbols

    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
    æĸ°åĬłåĿ¡
    -0.09
    åĬłæĭ¿å¤§
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    esis
    -0.08
    ness
    -0.07
    åľ¨
    -0.07
    ing
    -0.07
    !,
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    ed
    -0.07
    POSITIVE LOGITS
    ÙĥاÙģØŃØ©
    0.09
    urer
    0.09
    ²
    0.08
    ikker
    0.08
    arı
    0.08
    à¹Ģà¸ĸà¸Ńะ
    0.08
    æĪijå¦Ī
    0.08
    اء
    0.08
    worthy
    0.08
    ters
    0.07
    Activations Density 0.020%

    No Known Activations