© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17682
    Prev
    Next
    INDEX
    Explanations

    reference materials and standards

    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
    棲
    -0.09
    haal
    -0.08
    ahir
    -0.08
    Prediction
    -0.08
    _md
    -0.08
    attet
    -0.08
    otify
    -0.08
    relude
    -0.08
    -flex
    -0.08
    é¢ĦåĪ¤
    -0.08
    POSITIVE LOGITS
    æł¡åĩĨ
    0.13
     calibration
    0.11
     Calibration
    0.10
     standards
    0.10
    æł¡æŃ£
    0.09
     calibrated
    0.09
     cal
    0.09
    åŁºåĩĨ
    0.09
     reference
    0.09
     кали
    0.09
    Activations Density 0.034%

    No Known Activations