© 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. 13033
    Prev
    Next
    INDEX
    Explanations

    , followed by numbers

    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
    VES
    -0.08
    hov
    -0.08
    aliste
    -0.07
    ikian
    -0.07
    inha
    -0.07
    eut
    -0.07
    ĤŃ
    -0.07
    olumn
    -0.07
    δοÏĤ
    -0.07
    é¦ĸ饰
    -0.07
    POSITIVE LOGITS
    ارة
    0.07
    isson
    0.07
    ix
    0.07
    ายุ
    0.07
    inea
    0.06
    ocre
    0.06
    æ´
    0.06
    æĹłäºĭ
    0.06
    ctor
    0.06
    çĤ¹åľ¨
    0.06
    Activations Density 0.002%

    No Known Activations