© 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. 28422
    Prev
    Next
    INDEX
    Explanations

    sequence indexing

    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
    vsp
    -0.08
     dedi
    -0.07
    Äįaj
    -0.07
     Mayer
    -0.07
    atab
    -0.07
    å¹´å¤ļ
    -0.07
    ::$
    -0.07
    Õ®
    -0.07
    pisode
    -0.07
    ertest
    -0.07
    POSITIVE LOGITS
    jul
    0.07
    æĪĸèĢħæĺ¯
    0.06
    imid
    0.06
    istri
    0.06
    ital
    0.06
     Hearth
    0.06
    为é¢ĺ
    0.06
    0.06
    í
    0.06
     infix
    0.06
    Activations Density 0.018%

    No Known Activations