© 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. 57785
    Prev
    Next
    INDEX
    Explanations

    using to obtain

    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
    大è§Ĥ
    -0.07
    udeau
    -0.07
    符åIJĪè¦ģæ±Ĥ
    -0.07
    æĸ°æµªç½ij
    -0.07
    æľīåĬŁ
    -0.07
    athed
    -0.07
    à¸Ĭี
    -0.07
    রণ
    -0.07
    èµĦ讯ä¸Ńå¿ĥ
    -0.07
    สัà¸ĩ
    -0.07
    POSITIVE LOGITS
    åīįè¿°
    0.09
    ä¸Ĭè¿°äºĭå®ŀ
    0.09
     Tatsache
    0.09
     ØŃÙĤÙĬÙĤØ©
    0.08
     facts
    0.08
     symmetry
    0.08
     identities
    0.08
     already
    0.08
     Facts
    0.08
    äºĭå®ŀ
    0.08
    Activations Density 0.012%

    No Known Activations