© 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. 57975
    Prev
    Next
    INDEX
    Explanations

    adjustment and control

    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
    æĭľ
    -0.07
    Č↵
    -0.07
    oe
    -0.07
    羣çļĦ太
    -0.07
    оÑģÑĤо
    -0.07
    trup
    -0.06
     IDE
    -0.06
    _bases
    -0.06
    okit
    -0.06
     Medal
    -0.06
    POSITIVE LOGITS
     compens
    0.11
     adjustment
    0.10
     Adjustment
    0.10
    è°ĥæķ´
    0.09
    adjust
    0.09
     Adjust
    0.09
     adjust
    0.09
     adjusting
    0.09
    -adjust
    0.09
     adjustments
    0.09
    Activations Density 0.018%

    No Known Activations