© 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. 46372
    Prev
    Next
    INDEX
    Explanations

    chemical & scientific abbreviations

    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
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    交çļĦ
    -0.07
    -/
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    hoff
    -0.07
    -doc
    -0.06
    åıij表çļĦ
    -0.06
    oppi
    -0.06
    Ỽt
    -0.06
    udson
    -0.06
    POSITIVE LOGITS
    IFIER
    0.08
    endis
    0.07
    nene
    0.07
    óm
    0.07
    endi
    0.06
    rafo
    0.06
    antil
    0.06
    adel
    0.06
    ruz
    0.06
    缣
    0.06
    Activations Density 0.001%

    No Known Activations