© 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. 16293
    Prev
    Next
    INDEX
    Explanations

    event handlers and function calls

    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
    essen
    -0.07
    _DETECT
    -0.07
    annie
    -0.07
    bergen
    -0.07
    esser
    -0.07
    IGA
    -0.07
     cach
    -0.07
    _UC
    -0.06
    ä¸ĩçī©
    -0.06
    Attribute
    -0.06
    POSITIVE LOGITS
     calculation
    0.08
    代åħ¥
    0.08
    _defaults
    0.08
     Calculation
    0.07
    fav
    0.07
     Plug
    0.07
    æѤæŶçļĦ
    0.06
    à¸Ļิ
    0.06
    ughs
    0.06
    KeyType
    0.06
    Activations Density 0.021%

    No Known Activations