© 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. 45932
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.16
    ÛĮ
    -0.15
    ÑģÑı
    -0.14
    çļĦ
    -0.14
    nya
    -0.13
    ìĿĦ
    -0.12
    äºĨ
    -0.11
    à§ĩর
    -0.11
    ãĤĪãģĨãģ«
    -0.11
    Ùĩ
    -0.10
    POSITIVE LOGITS
    и
    0.13
    ÙĬ
    0.11
    Ø©
    0.11
    ÑģÑĮ
    0.10
    erior
    0.10
    sWith
    0.09
    eration
    0.09
    àµį
    0.09
    eu
    0.09
    ness
    0.09
    Activations Density 0.009%

    No Known Activations