© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15181
    Prev
    Next
    INDEX
    Explanations

    studies on

    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
    eland
    -0.07
    ä¸īå¹´æĿ¥
    -0.07
    ackers
    -0.07
    OND
    -0.07
    æ»ĭ润
    -0.07
    opter
    -0.07
     rech
    -0.07
    оÑĩно
    -0.06
     Kushner
    -0.06
    allee
    -0.06
    POSITIVE LOGITS
    çIJĨ顺
    0.09
    笳
    0.08
    Rule
    0.07
     conventions
    0.07
    æİĴåĪĹ
    0.07
     outright
    0.07
    éĻµ
    0.07
    ç¼ĸæİĴ
    0.07
     rearr
    0.07
    ç³»æķ°
    0.07
    Activations Density 0.002%

    No Known Activations