© 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. 11343
    Prev
    Next
    INDEX
    Explanations

    protect, support, improve

    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
    ugno
    -0.10
    _HE
    -0.07
    USR
    -0.07
    究åħ¶åİŁåĽł
    -0.07
    _AV
    -0.07
    é«ĺ度éĩįè§Ĩ
    -0.07
    arau
    -0.07
     fortunately
    -0.07
     ÙĪست
    -0.07
    igrams
    -0.07
    POSITIVE LOGITS
    并æıIJä¾Ľ
    0.10
    并使
    0.09
    èµ·çĿĢ
    0.09
    çŃīä½ľçĶ¨
    0.09
    åĴĮ帮åĬ©
    0.09
    ä¸įèĩ³äºİ
    0.08
     ÙĪتÙĪÙģÙĬر
    0.08
    éĺ²æŃ¢
    0.08
    顺便
    0.08
    ä¸įåı¯ç¼ºå°ij
    0.08
    Activations Density 0.191%

    No Known Activations