© 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. 65239
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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¸İç»´æĬ¤
    -0.07
    禺
    -0.07
    _ABI
    -0.07
     ç§ģ
    -0.06
    åĨħ容çļĦ
    -0.06
    èĤļ
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    éģįéĩİ
    -0.06
    ä¹ĭä½ľ
    -0.06
    hetto
    -0.06
    POSITIVE LOGITS
     www
    0.09
    www
    0.09
    arkin
    0.08
    åĿĢ
    0.08
    thon
    0.08
     situs
    0.07
    说好
    0.07
    (dot
    0.07
    lify
    0.07
    ç½ijåĿĢ
    0.07
    Activations Density 0.350%

    No Known Activations