© 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. 12375
    Prev
    Next
    INDEX
    Explanations

    greek letters, mathematical variables

    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
    nok
    -0.07
    ä¸įåıij
    -0.06
    iski
    -0.06
    abase
    -0.06
    inci
    -0.06
     symp
    -0.06
    缸åħ³éĹ®çŃĶ
    -0.06
     semiclass
    -0.06
    no
    -0.06
     MUST
    -0.06
    POSITIVE LOGITS
    éħ¥
    0.08
    lobber
    0.07
    ostra
    0.07
    -desktop
    0.07
    æľ¬çİĭ
    0.07
     délais
    0.07
    éĿĴåŁİ
    0.07
    lej
    0.07
    valuator
    0.07
    esseract
    0.07
    Activations Density 0.025%

    No Known Activations