© 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. 51622
    Prev
    Next
    INDEX
    Explanations

    . Advanced, Discovery, How

    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
    ä¸įè¿ĺ
    -0.07
    .(*
    -0.06
    ö
    -0.06
    便
    -0.06
    Âł
    -0.06
    vlak
    -0.06
    iaz
    -0.06
    asure
    -0.05
    FIX
    -0.05
     Merr
    -0.05
    POSITIVE LOGITS
    æ´Ľä¼Ĭ
    0.09
    зÑĮ
    0.08
    erja
    0.08
     sain
    0.07
    PTR
    0.07
    å¤ļ好
    0.07
     oszt
    0.07
    ÑĢÑĥг
    0.07
    HOOK
    0.07
    Looper
    0.07
    Activations Density 0.583%

    No Known Activations