© 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. 55859
    Prev
    Next
    INDEX
    Explanations

    quantum, physics, mathematics, statistics

    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
    ÙĪز
    -0.08
    RetVal
    -0.08
    -gnu
    -0.07
    ä¸ĵæłı
    -0.07
    /loading
    -0.07
    omor
    -0.07
    ego
    -0.07
    è¡Ģ红
    -0.06
     Grosso
    -0.06
    é½
    -0.06
    POSITIVE LOGITS
    çīĪçļĦ
    0.14
    çīĪæľ¬çļĦ
    0.12
     versions
    0.10
     version
    0.09
    çīĪ
    0.09
    -version
    0.08
    çīĪæľ¬
    0.08
     Version
    0.07
    ulti
    0.07
    ement
    0.07
    Activations Density 0.880%

    No Known Activations