© 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. 49785
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    为äºĨæĽ´å¥½çļĦ
    -0.08
    anner
    -0.08
    åľ°åĿĢä½įäºİ
    -0.08
    igr
    -0.08
    åħĪéĶĭ模èĮĥ
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    යà·Ĵ
    -0.07
    çŃł
    -0.07
    å°¼æĸ¯
    -0.07
    kinson
    -0.07
    POSITIVE LOGITS
    ymbols
    0.10
    ç¡®
    0.07
    ought
    0.07
    kaar
    0.07
    accep
    0.07
     constants
    0.07
    symbols
    0.06
    å°½éĩıå°ij
    0.06
    äºĨ
    0.06
    ä¸įå°½
    0.06
    Activations Density 0.003%

    No Known Activations