© 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. 30461
    Prev
    Next
    INDEX
    Explanations

    questions with numbers or dates

    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
    Ratio
    -0.09
    ratio
    -0.08
    åŃ¦ä»¥èĩ´
    -0.08
    otka
    -0.08
    orted
    -0.08
    ilter
    -0.08
    _scaling
    -0.08
     Ratio
    -0.07
    rol
    -0.07
    åģļ人
    -0.07
    POSITIVE LOGITS
     subtract
    0.08
     subtraction
    0.07
    沸
    0.07
    åIJĪ并
    0.06
     decre
    0.06
    merge
    0.06
    补足
    0.06
     merge
    0.06
    pat
    0.06
    subtract
    0.06
    Activations Density 0.012%

    No Known Activations