© 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. 38749
    Prev
    Next
    INDEX
    Explanations

    self-determination

    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
    yscale
    -0.08
    utenberg
    -0.08
     WHATSOEVER
    -0.08
    $__
    -0.08
    起订
    -0.08
    ymar
    -0.07
    ç§Ģ丽
    -0.07
    esai
    -0.07
    çĿ¦
    -0.07
    è¿ĺæ¸ħ
    -0.07
    POSITIVE LOGITS
    客ä½ĵ
    0.10
    æĬ½è±¡
    0.08
    åĪĽè®¾
    0.08
    æ³ķå¾ĭåħ³ç³»
    0.08
    侵害
    0.07
    æŁ¥æĺİ
    0.07
    妨害
    0.07
    æ°ijæ³ķ
    0.07
    ä¸Ńç«ĭ
    0.07
    çijķçĸµ
    0.07
    Activations Density 0.001%

    No Known Activations