© 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. 38112
    Prev
    Next
    INDEX
    Explanations

    numbered lists; symbolism metaphor

    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
    被åĪ«äºº
    -0.07
    ç»ĵæŀĦç®Ģåįķ
    -0.07
    å®īå®ī
    -0.06
    _SIMPLE
    -0.06
    å±ĢéĻIJ
    -0.06
    éĿĴ涩
    -0.06
    _guard
    -0.06
     solely
    -0.06
     ar
    -0.06
    ç®Ģæ´ģ
    -0.06
    POSITIVE LOGITS
    æľīå¤ļç§į
    0.11
    ä¸įä»ħæľī
    0.11
    åħ·æľī丰å¯ĮçļĦ
    0.10
     multif
    0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.10
    å¤ļç§į
    0.09
    æĹ¢è¦ģ
    0.09
    æĹ¢åı¯ä»¥
    0.09
    形形èī²
    0.09
     vielseit
    0.09
    Activations Density 0.184%

    No Known Activations