© 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. 51568
    Prev
    Next
    INDEX
    Explanations

    consider + action

    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
    ertes
    -0.09
     supposedly
    -0.08
    xad
    -0.07
    odom
    -0.07
    erte
    -0.07
    _singular
    -0.07
    errupt
    -0.07
    ctu
    -0.07
    thers
    -0.07
    ern
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĸ¹å¼ı
    0.10
    aste
    0.09
    æĢ§åľ°
    0.07
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    å°Ĩ对
    0.07
    è¿Ļ便æĺ¯
    0.07
    以ä¸ĭåĩłçĤ¹
    0.07
    以ä¸ĭåĩłç§į
    0.07
    abil
    0.07
    Activations Density 0.007%

    No Known Activations