© 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. 61325
    Prev
    Next
    INDEX
    Explanations

    set of mathematical objects

    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
    heen
    -0.10
    erweise
    -0.10
    enzo
    -0.09
    Ø«ÙĤ
    -0.09
    trut
    -0.08
     ÑĢаÑģÑģÑĩиÑĤÑĭваÑĤÑĮ
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ught
    -0.08
    ست
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    POSITIVE LOGITS
    tlement
    0.16
    tle
    0.12
    sockopt
    0.10
    ings
    0.10
    uptools
    0.09
    åŃIJéĩĮ
    0.09
    mate
    0.08
    ellite
    0.08
    istical
    0.08
    timeofday
    0.08
    Activations Density 0.049%

    No Known Activations