© 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. 56612
    Prev
    Next
    INDEX
    Explanations

    hands-on experience

    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
    äºĭä¸ļä¸Ĭ
    -0.08
     sỹ
    -0.08
    çłĤç³ĸ
    -0.08
     Hubb
    -0.07
    åıĬæĹ¶æ²»çĸĹ
    -0.07
    è¶Ĭæĥ³
    -0.07
    ẩn
    -0.07
    æŀĦ建åĴĮè°IJ
    -0.07
    çŁ
    -0.07
    aliz
    -0.07
    POSITIVE LOGITS
     exper
    0.11
    åĬ¨æīĭ
    0.11
    åĬ¨æīĭèĥ½åĬĽ
    0.10
    hands
    0.10
    ä½ĵéªĮ
    0.10
    å®ŀè·µ
    0.10
     experience
    0.09
    ç»ıéªĮçļĦ
    0.09
    exper
    0.09
    亲身ä½ĵéªĮ
    0.09
    Activations Density 0.049%

    No Known Activations