© 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. 39090
    Prev
    Next
    INDEX
    Explanations

    but, yet

    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
    è¹Ī
    -0.07
    ogi
    -0.07
    _SID
    -0.06
    ั
    -0.06
    оÑĩÑĮ
    -0.06
    oyer
    -0.06
    æ¢ĵ
    -0.06
    èĬ³åįİ
    -0.06
    æĺ¯æľĢéĩįè¦ģçļĦ
    -0.06
    tent
    -0.06
    POSITIVE LOGITS
    ä»įèĥ½
    0.19
    ä¸įå½±åĵį
    0.17
    ä¾ĿçĦ¶
    0.17
    ä»įåı¯
    0.17
    ä¸įä¼ļå½±åĵį
    0.16
    ä»į
    0.15
     still
    0.15
     maintains
    0.14
    åį´ä¾ĿçĦ¶
    0.14
    still
    0.14
    Activations Density 0.191%

    No Known Activations