© 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. 22101
    Prev
    Next
    INDEX
    Explanations

    java, android, php, javascript, EE

    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
    æĪĸéĥ¨åĪĨ
    -0.08
    ihi
    -0.07
    æĪĸå°ij
    -0.06
    äºĭæķħçļĦåıijçĶŁ
    -0.06
    heimer
    -0.06
    unit
    -0.06
    .gt
    -0.06
    heet
    -0.06
    åĴĮä¸ļåĬ¡
    -0.06
    दà¥ĩश
    -0.06
    POSITIVE LOGITS
    çŃīé¢ĨåŁŁ
    0.09
    ]-$
    0.08
    çŃīé¢ĨåŁŁçļĦ
    0.07
    -aware
    0.07
    æ·±åĪ»é¢Ĩä¼ļ
    0.07
    çŃī缸åħ³
    0.07
    ÑĢке
    0.07
    ahan
    0.07
    继ç»Ńåħ³æ³¨
    0.07
    fica
    0.07
    Activations Density 0.159%

    No Known Activations