© 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. 22296
    Prev
    Next
    INDEX
    Explanations

    suspension, dispersion, solution, infusion

    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
     thrust
    -0.07
     appended
    -0.06
    åıĺç§į
    -0.06
    æ¥ŀ
    -0.06
    end
    -0.06
     ÐŁÑĢоÑģмоÑĤÑĢов
    -0.06
    awah
    -0.06
    åıī
    -0.06
    æĹģ
    -0.06
    T
    -0.06
    POSITIVE LOGITS
     Concent
    0.09
     concentrate
    0.09
     koncent
    0.09
    ĥģ
    0.08
     concentration
    0.08
    istar
    0.08
     concentrated
    0.08
    âĢķâĢķâĢķâĢķ
    0.08
    HTTPHeader
    0.08
    çĻ¾éĩĮ
    0.08
    Activations Density 0.058%

    No Known Activations