© 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. 3991
    Prev
    Next
    INDEX
    Explanations

    many small

    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
    èĮĥ
    -0.08
    以å¤ĸçļĦ
    -0.07
    ogie
    -0.07
    raven
    -0.06
    rak
    -0.06
    以å¤ĸ
    -0.06
    isure
    -0.06
    æľīæŶä¼ļ
    -0.06
     Extra
    -0.06
    两åIJį
    -0.06
    POSITIVE LOGITS
     countless
    0.14
    æĹłæķ°ä¸ª
    0.13
    æĹłæķ°çļĦ
    0.12
     myriad
    0.12
     collectively
    0.12
     thousands
    0.11
     множеÑģÑĤво
    0.11
     multitude
    0.11
    æĹłæķ°
    0.11
    æĪIJåįĥ
    0.11
    Activations Density 0.110%

    No Known Activations