© 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. 60188
    Prev
    Next
    INDEX
    Explanations

    which question

    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
     *:
    -0.07
    æīĢè°ĵ
    -0.06
     Doe
    -0.06
    æģ
    -0.06
    ä½ľä¸ºä¸Ģ个
    -0.06
    æīĢè°ĵçļĦ
    -0.06
    igner
    -0.06
    oug
    -0.06
    èĩ´çļĦ
    -0.06
    åĪĨæĪIJ
    -0.06
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩéĥ½
    0.09
     itulah
    0.08
    ç³»ç»Łå°Ĩ
    0.08
    çļĦ人ä¼ļ
    0.08
    åĵªç§į
    0.08
     circumstance
    0.08
     inilah
    0.08
    æ´»åĬ¨åĩĨå¤ĩ
    0.08
    ufe
    0.07
    ä½ķç§į
    0.07
    Activations Density 0.112%

    No Known Activations