© 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. 46945
    Prev
    Next
    INDEX
    Explanations

    novel method or mutation

    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
    hek
    -0.07
    루
    -0.07
     Kuk
    -0.07
    æĹłåĬŁ
    -0.07
    ouvoir
    -0.07
    ÄĽÅĻ
    -0.07
    uro
    -0.07
    illo
    -0.07
    èīºæľ¯ä½ľåĵģ
    -0.07
    ivities
    -0.07
    POSITIVE LOGITS
     Mc
    0.07
    ä¸Ģè§ģ
    0.06
    è´Łè´£ç»Ħç»ĩ
    0.06
    alde
    0.06
    ÙĤدÙĬÙħ
    0.06
     Octubre
    0.06
    æ¼
    0.06
     ÄIJô
    0.06
    inoa
    0.06
    åŃ
    0.06
    Activations Density 0.001%

    No Known Activations