© 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. 49503
    Prev
    Next
    INDEX
    Explanations

    languages and grammar

    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¸įæĥĬ
    -0.09
    nel
    -0.08
    InSection
    -0.08
    ä¸įæ²»
    -0.08
    onsel
    -0.08
    oule
    -0.08
    igts
    -0.08
    óri
    -0.07
    ÑģÑĭпа
    -0.07
    าà¸Ļิ
    -0.07
    POSITIVE LOGITS
     native
    0.10
    -language
    0.10
    è¯Ńæ³ķ
    0.09
    è¿ĻéŨ
    0.09
    -speaking
    0.09
     gramm
    0.09
    æ¯įè¯Ń
    0.09
    æĺ¯ä¸ĢéŨ
    0.08
     language
    0.08
     grammar
    0.08
    Activations Density 0.089%

    No Known Activations