© 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. 25720
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    ugg
    -0.09
    TPL
    -0.09
     ()->
    -0.08
    æĿĥåĴĮ
    -0.08
    è¿ĻäºĽä¸ľè¥¿
    -0.08
    æĢ§ä¸İ
    -0.08
    æĢ§åıĬ
    -0.08
    awat
    -0.07
    çĦī
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.07
    POSITIVE LOGITS
    以åĨħçļĦ
    0.08
    Õ¡Õ¶
    0.08
    以ä¸ĬçļĦ
    0.08
    åıĬ以ä¸ĬçļĦ
    0.07
    ãģļãģ¤
    0.07
    å·¦åı³çļĦ
    0.07
    ì§ľ
    0.07
    ï¼Į
    0.07
    以åĨħ
    0.07
    éĹ¹
    0.07
    Activations Density 0.010%

    No Known Activations