© 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. 49006
    Prev
    Next
    INDEX
    Explanations

    satisfies conditions/constraints

    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
    Õ¡Õ¯
    -0.07
     Gì
    -0.07
    FromString
    -0.07
    è¯ģæį®è¯ģæĺİ
    -0.07
     Anything
    -0.07
    _DU
    -0.07
    èĭ±æĸĩåŃĹ
    -0.07
    çļĦæĸ¹æ³ķæĿ¥
    -0.07
    æľīä¸Ģéĥ¨åĪĨ
    -0.06
     ÙħختÙĦÙģÛĮ
    -0.06
    POSITIVE LOGITS
     constraints
    0.10
    Constraints
    0.10
    _constraints
    0.09
     given
    0.08
    constraints
    0.08
    iren
    0.08
    conditions
    0.08
    ç»Ļå®ļ
    0.08
    æĹ¢å®ļ
    0.08
    éĩįéĩįçļĦ
    0.08
    Activations Density 0.035%

    No Known Activations