© 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. 55865
    Prev
    Next
    INDEX
    Explanations

    scientific papers and journals

    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
    èķĬ
    -0.07
    yll
    -0.07
    æijĩæijĩ
    -0.07
    è¿ĩ硬
    -0.07
    å¼ģ
    -0.06
    çĶ¨å®Į
    -0.06
    åIJĿ
    -0.06
    аÑĩ
    -0.06
    ikos
    -0.06
    sd
    -0.06
    POSITIVE LOGITS
    以èĩªå·±çļĦ
    0.08
    太平
    0.07
    å¿«å¿«ä¹IJ
    0.07
    åĴĮå¹³
    0.07
    ç¼ĵåĴĮ
    0.07
    轻微
    0.06
    bert
    0.06
    Bow
    0.06
    pond
    0.06
    éŀł
    0.06
    Activations Density 0.002%

    No Known Activations