© 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. 29096
    Prev
    Next
    INDEX
    Explanations

    have any problems

    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
    áºŃu
    -0.08
    人å¿ĥ
    -0.08
    æ¨ĭ
    -0.07
    æ¢Ń
    -0.07
     fig
    -0.06
    olos
    -0.06
    outu
    -0.06
    Mocks
    -0.06
     reg
    -0.06
    åĩºä¸Ģçīĩ
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķ
    0.10
    çļĦä»»ä½ķ
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.09
     anything
    0.09
    ught
    0.08
    ä»»ä½ķä¸Ģç§į
    0.08
     irgend
    0.08
    ä»»ä½ķä¸Ģ个
    0.08
     anytime
    0.08
    yscale
    0.08
    Activations Density 0.294%

    No Known Activations