© 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. 22018
    Prev
    Next
    INDEX
    Explanations

    code files

    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
    详ç»Ĩæııè¿°
    -0.07
    ullet
    -0.07
     (âĢ¦)
    -0.07
    _FETCH
    -0.07
    ught
    -0.07
    [âĢ¦]
    -0.06
    husus
    -0.06
    çĻ»å½ķåIJİæŁ¥çľĭ
    -0.06
    entina
    -0.06
    åħ¨æľ¬å°ı说
    -0.06
    POSITIVE LOGITS
    两ç§įæĸ¹å¼ı
    0.09
    solution
    0.08
    è¿Ļç§įæĸ¹æ³ķ
    0.08
    Solution
    0.08
     Kors
    0.08
     Solution
    0.08
    çıŃä¸Ĭ
    0.08
    ìĤŃ
    0.07
     ganh
    0.07
     solution
    0.07
    Activations Density 0.205%

    No Known Activations