© 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. 41286
    Prev
    Next
    INDEX
    Explanations

    look or let's

    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
    ipel
    -0.08
    íħIJ
    -0.08
    å¹´ä¸ĢåŃ£åº¦
    -0.08
    å§Ĩ
    -0.07
    zes
    -0.07
    øgne
    -0.07
    anker
    -0.07
     viá»ĩc
    -0.07
    Powered
    -0.07
    riad
    -0.07
    POSITIVE LOGITS
    prat
    0.06
    æī¬éķ¿
    0.06
    ilah
    0.06
    жай
    0.06
    ixin
    0.06
     again
    0.06
    رÙĪÛĮ
    0.06
    âteau
    0.06
     recap
    0.06
    .oracle
    0.06
    Activations Density 0.008%

    No Known Activations