© 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. 46279
    Prev
    Next
    INDEX
    Explanations

    VO2max and clearance measurements

    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
    okr
    -0.08
    kek
    -0.08
    {_
    -0.08
     vaccin
    -0.08
    建工
    -0.07
    çĿIJ
    -0.07
    zal
    -0.07
    ejm
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
    _grade
    -0.07
    POSITIVE LOGITS
    -volume
    0.09
     perf
    0.09
     measured
    0.08
     Volume
    0.08
     Total
    0.08
     volume
    0.08
    iggins
    0.08
     Perf
    0.08
     efficiency
    0.08
     total
    0.08
    Activations Density 0.099%

    No Known Activations