© 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. 12750
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons and calculations

    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
    orie
    -0.06
    ÏĦει
    -0.06
    irat
    -0.06
    adop
    -0.06
    èĨĽ
    -0.06
    éĽĨæĪIJ
    -0.06
    积
    -0.06
    åĽŀ访
    -0.06
     HACK
    -0.06
    _DEPRECATED
    -0.06
    POSITIVE LOGITS
    YTE
    0.08
    ÙĬÙĩ
    0.08
    ÙĬØ·
    0.07
     Kremlin
    0.07
     gew
    0.07
     scram
    0.07
    imini
    0.07
    çĦ¡ãģĹ
    0.07
    ÛĮز
    0.07
    ihn
    0.06
    Activations Density 0.022%

    No Known Activations