© 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. 46118
    Prev
    Next
    INDEX
    Explanations

    SQL clauses and conditions

    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
    вÑĸй
    -0.08
    æĥħåĨµåĪĨæŀIJ
    -0.08
    inqu
    -0.08
    è¿ĺåı¯ä»¥åľ¨
    -0.08
    opa
    -0.08
    ],&
    -0.07
    portun
    -0.07
    ÄĽz
    -0.07
     xá»ī
    -0.07
    rement
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.17
    并ä¸Ķ
    0.15
    ä¸Ķåľ¨
    0.14
    ä¸Ķæľī
    0.13
    並ä¸Ķ
    0.12
    并ä¸Ķåľ¨
    0.11
    ä¸Ķåħ·æľī
    0.10
    ãģĭãģ¤
    0.10
    èĢĮä¸Ķ
    0.10
    ä¸Ķä¸į
    0.10
    Activations Density 0.037%

    No Known Activations