© 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. 64341
    Prev
    Next
    INDEX
    Explanations

    musical instruments, naked man, sun, seeds

    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
    游åĪĥæľīä½Ļ
    -0.07
    clr
    -0.07
    AndUpdate
    -0.07
    upd
    -0.07
     Cant
    -0.07
    èѦéĴŁ
    -0.07
    大年åĪĿ
    -0.07
    已累计
    -0.06
    è¾ħ以
    -0.06
    ëĭ¥
    -0.06
    POSITIVE LOGITS
    ç»ĻåĪ«äºº
    0.08
    纵横
    0.08
    ç»Ļ人
    0.07
    ä¹Łå¥½
    0.07
     disp
    0.07
    æīį好
    0.07
    ilver
    0.07
    æ¯Ķåĸ»
    0.07
    æŀ¶ä¸Ĭ
    0.07
    å¤ĸéĿ¢çļĦ
    0.07
    Activations Density 0.003%

    No Known Activations