© 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. 63558
    Prev
    Next
    INDEX
    Explanations

    recommendation

    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
    lef
    -0.09
    obia
    -0.08
    borne
    -0.08
    æľŁå¾ħæĤ¨çļĦ
    -0.08
    uação
    -0.08
    欢è¿İåIJĦä½į
    -0.07
    bine
    -0.07
    lukan
    -0.07
    Åijd
    -0.07
    acters
    -0.07
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.11
     ìĤ¬íķŃ
    0.10
    äºĭéłħ
    0.10
     ìĤ¬íķŃìĿĢ
    0.08
    è¡Įäºĭ
    0.08
    ëĮĢë¡ľ
    0.08
    ãi
    0.08
     ìĤ¬íķŃìĿĦ
    0.08
    åĴĮé¼ĵåĬ±
    0.08
     ëĮĢë¡ľ
    0.07
    Activations Density 0.058%

    No Known Activations