© 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. 27827
    Prev
    Next
    INDEX
    Explanations

    Category:1747 deaths

    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
    Unnamed
    -0.07
    æĹłæķ°ä¸ª
    -0.07
    èĸª
    -0.06
    bor
    -0.06
    èijµèĬ±
    -0.06
    ('.'
    -0.06
    ench
    -0.06
     unt
    -0.06
    xCA
    -0.06
    #__
    -0.06
    POSITIVE LOGITS
     definitely
    0.08
     famously
    0.08
    classic
    0.07
     Brotherhood
    0.07
    utih
    0.07
     Definitely
    0.07
     famos
    0.07
    士æŀĹ
    0.07
    ново
    0.07
    phin
    0.07
    Activations Density 0.242%

    No Known Activations