© 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. 20012
    Prev
    Next
    INDEX
    Explanations

    every existential

    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
    istring
    -0.10
    å·¡è§Ĩåijĺ
    -0.08
    oret
    -0.08
    æĬĺåIJĪ
    -0.07
    ancode
    -0.07
    å«©èĤ¤
    -0.07
    _ATTRIB
    -0.07
     bureaucr
    -0.07
    ache
    -0.07
    è¿ĻäºĽåĽłç´ł
    -0.07
    POSITIVE LOGITS
    every
    0.10
    Every
    0.09
     every
    0.09
     Every
    0.08
    æ¯ıå½ĵ
    0.08
     Elek
    0.07
     closed
    0.07
    ä»»
    0.07
     whenever
    0.07
     Whenever
    0.07
    Activations Density 0.025%

    No Known Activations