© 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. 7387
    Prev
    Next
    INDEX
    Explanations

    cursor position or caret position

    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
     polic
    -0.07
    å·²ç»ıæľī
    -0.07
    åħ¨æĺ¯
    -0.06
    åīįè·¯
    -0.06
    èĩªè¾¾
    -0.06
    çĦ¶å¤§
    -0.06
    á»Ļp
    -0.06
     kats
    -0.06
    ombine
    -0.06
     grouped
    -0.06
    POSITIVE LOGITS
    çļĦä½įç½®
    0.13
    移åĬ¨
    0.12
    ä½įç½®
    0.12
    shift
    0.12
    Moved
    0.11
     ìĿ´ëıĻ
    0.11
     shifting
    0.11
     shifted
    0.11
    çļĦ移åĬ¨
    0.11
    移åĭķ
    0.11
    Activations Density 0.156%

    No Known Activations