© 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. 45882
    Prev
    Next
    INDEX
    Explanations

    ratings and scores

    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
    è¾
    -0.07
    bs
    -0.06
     vir
    -0.06
    rier
    -0.06
     commonly
    -0.06
    æľ¬æĬ¥
    -0.06
    ï¬ģ
    -0.06
    è®Ń
    -0.05
    los
    -0.05
    å·¥ç¨ĭçŃī
    -0.05
    POSITIVE LOGITS
    æİ¥ä¸ĭ
    0.08
    avic
    0.08
    linger
    0.07
    pjes
    0.07
    ichern
    0.07
    WithValue
    0.07
    uhi
    0.07
    ÃŃž
    0.07
    аÑģÑĤ
    0.07
    ajib
    0.07
    Activations Density 0.078%

    No Known Activations