© 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. 38226
    Prev
    Next
    INDEX
    Explanations

    shows that

    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
    享
    -0.07
    çĻ½æ°´
    -0.07
    ])[
    -0.07
    INN
    -0.07
     пÑĥÑĤ
    -0.07
    å¤ļç±³
    -0.07
    erdo
    -0.07
     Miscellaneous
    -0.07
    agli
    -0.06
    _frontend
    -0.06
    POSITIVE LOGITS
     regimes
    0.08
     dependence
    0.08
    å¢ŀéķ¿çļĦ
    0.08
    arity
    0.08
    åıijçİ°èĩªå·±çļĦ
    0.08
    åķ¬
    0.08
    æľī趣çļĦæĺ¯
    0.08
    éĽ£æĢª
    0.07
     regime
    0.07
    çİ°å®ŀæĦıä¹ī
    0.07
    Activations Density 0.025%

    No Known Activations