© 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. 25213
    Prev
    Next
    INDEX
    Explanations

    numbers and formatting

    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
    inals
    -0.07
    оÑģÑĤ
    -0.07
    izr
    -0.07
    举é£İ
    -0.07
     PURE
    -0.07
    cion
    -0.07
    mals
    -0.06
    PURE
    -0.06
     orgy
    -0.06
    สุ
    -0.06
    POSITIVE LOGITS
    åŃ¦ä¹łåĨħ容
    0.07
    使å®ĥ
    0.07
    æīįæĻº
    0.07
    éĩĩ
    0.07
    å¿ĥåºķ
    0.06
    _MATH
    0.06
    æľįåĬ¡åĨħ容
    0.06
    ÄŁÃ¼
    0.06
    äºĭçī©çļĦ
    0.06
    æİ¡
    0.06
    Activations Density 0.001%

    No Known Activations