© 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. 27281
    Prev
    Next
    INDEX
    Explanations

    initialization delayed

    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
     unlocked
    -0.07
    IRC
    -0.06
    Ĩ
    -0.06
    æĬĬåŃ¦ä¹ł
    -0.06
    ว
    -0.06
    ipot
    -0.06
    argas
    -0.06
    ä¹ĭæīĢ以
    -0.06
     reasoned
    -0.06
    ุà¸ĩ
    -0.06
    POSITIVE LOGITS
    顾åIJįæĢĿ
    0.09
    æľī为
    0.08
    ’h
    0.07
    åħ¬åı·
    0.07
    aqu
    0.07
    orgen
    0.07
    ÛĮدÛĮ
    0.07
    ÙĩÙĪر
    0.07
    æİ
    0.07
    gee
    0.07
    Activations Density 0.021%

    No Known Activations