© 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. 51220
    Prev
    Next
    INDEX
    Explanations

    summary lead ore

    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
    emens
    -0.07
    omb
    -0.07
    åľ¨ä¸ĭ
    -0.07
    e
    -0.07
    æ³ĵ
    -0.06
     Kush
    -0.06
    ×ķס
    -0.06
    chor
    -0.06
    _TERM
    -0.06
    ç®Ķ
    -0.06
    POSITIVE LOGITS
    irl
    0.08
    etak
    0.08
    árs
    0.08
    çĤ¹åĩ»è¿Ľåħ¥
    0.08
    ãģ¿ãģ¤
    0.07
    å§ij
    0.07
    utip
    0.07
    lemi
    0.07
    kania
    0.07
    à¸Ķาà¸Ļ
    0.07
    Activations Density 0.014%

    No Known Activations