© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48348
    Prev
    Next
    INDEX
    Explanations

    CCP, FT, MMP, LPG, IP acronyms

    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
    incer
    -0.08
    antly
    -0.08
    ably
    -0.07
     alike
    -0.07
    uci
    -0.07
    æĽ´ä¸įä¼ļ
    -0.07
    å¼Ĥ
    -0.07
    ahui
    -0.07
    ä¹ĭå®Ŀ
    -0.07
    FUN
    -0.07
    POSITIVE LOGITS
    -Cs
    0.07
    otas
    0.06
    edy
    0.06
    pery
    0.06
    esh
    0.06
    ped
    0.06
    PED
    0.06
    chants
    0.06
    plits
    0.06
    çªĿ
    0.06
    Activations Density 0.740%

    No Known Activations