© 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. 15440
    Prev
    Next
    INDEX
    Explanations

    Milton Freewater

    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
    è¯¥ç³»ç»Ł
    -0.07
    uil
    -0.07
    urr
    -0.07
    bench
    -0.07
    kee
    -0.07
     entirety
    -0.07
    ä¸Ģ段æŶéĹ´çļĦ
    -0.07
    æĽ´ä¸º
    -0.06
    allo
    -0.06
    +=
    -0.06
    POSITIVE LOGITS
    cak
    0.08
     astronom
    0.07
    -Type
    0.07
    çļĻ
    0.07
    /Instruction
    0.07
     Ney
    0.07
    ç¥ĸ
    0.07
    eteil
    0.07
    ÑĦилÑĮ
    0.07
     reconnaissance
    0.07
    Activations Density 0.001%

    No Known Activations