© 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. 10585
    Prev
    Next
    INDEX
    Explanations

    access point

    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
    è¿Ļ件äºĭ
    -0.07
    ستر
    -0.07
    è¿ĩä¸įåİ»
    -0.07
    ickness
    -0.06
    è¿Ļ件äºĭæĥħ
    -0.06
    ä½Ĩæĺ¯ä»ĸ
    -0.06
    ener
    -0.06
    ^^
    -0.06
    olic
    -0.06
    geh
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.26
    æ¯Ķå¦Ĥ
    0.22
     напÑĢимеÑĢ
    0.20
    напÑĢимеÑĢ
    0.19
     ÐĿапÑĢимеÑĢ
    0.19
    ä¾ĭãģĪãģ°
    0.19
    诸å¦Ĥ
    0.19
    ãģŁãģ¨ãģĪãģ°
    0.17
    èѬå¦Ĥ
    0.16
     misalnya
    0.16
    Activations Density 0.078%

    No Known Activations