© 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. 45873
    Prev
    Next
    INDEX
    Explanations

    measurement metrics

    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
    ffel
    -0.08
     jud
    -0.07
    è¾ĥ强
    -0.07
    é¹ĥ
    -0.07
    ÙĪاÙĤع
    -0.06
    opol
    -0.06
    è¾ĥå¼±
    -0.06
     Wirkung
    -0.06
    erias
    -0.06
    ente
    -0.06
    POSITIVE LOGITS
    total
    0.09
    normalized
    0.09
     normalized
    0.09
     ratio
    0.08
     total
    0.08
    asio
    0.08
     versus
    0.08
    -total
    0.08
    _normalized
    0.07
    Normalized
    0.07
    Activations Density 0.191%

    No Known Activations