© 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. 58386
    Prev
    Next
    INDEX
    Explanations

    Yes / true / constant

    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
     Confeder
    -0.08
    instead
    -0.07
     ÐĴмеÑģÑĤо
    -0.07
     instead
    -0.07
    æľīåºıæİ¨è¿Ľ
    -0.07
    è´¡
    -0.07
    ezet
    -0.07
    úst
    -0.07
    صاد
    -0.07
    OCKET
    -0.07
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.08
     barring
    0.08
     yes
    0.08
    èĩ³å°ijåľ¨
    0.08
    åīįæıIJ
    0.08
    åı¯ä»¥ä¿Ŀè¯ģ
    0.08
    åı¯éĿłæĢ§
    0.08
    åIJ¦
    0.07
    Meet
    0.07
    åıªè¦ģæĺ¯
    0.07
    Activations Density 0.004%

    No Known Activations