© 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. 23773
    Prev
    Next
    INDEX
    Explanations

    a/with + adjective/noun

    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
    ä»»ä½ķåħ¶ä»ĸ
    -0.08
    ipse
    -0.08
     sane
    -0.07
    essin
    -0.07
    ä¸ĢæĿ¡æĿ¡
    -0.07
    eppe
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    ĵĺ
    -0.07
     Lor
    -0.07
    ptime
    -0.07
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.08
    æ¶īåıĬ
    0.07
    -variable
    0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
    æĢĿ
    0.07
     requires
    0.07
     Variable
    0.07
    æ¯Ķè¾ĥå¤įæĿĤ
    0.06
    æĺİç¡®è¦ģæ±Ĥ
    0.06
     variable
    0.06
    Activations Density 0.037%

    No Known Activations