© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13997
    Prev
    Next
    INDEX
    Explanations

    preliminary, prior, before

    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
    croll
    -0.08
    adrat
    -0.07
    udi
    -0.07
    ä»Ĭå¾ĮãĤĤ
    -0.07
    æľ¬æĸĩéĵ¾æİ¥
    -0.07
    gade
    -0.07
    æľ¬åĪ¤åĨ³
    -0.07
    alc
    -0.07
    ä»ĬåIJİ
    -0.07
     menda
    -0.07
    POSITIVE LOGITS
     preliminary
    0.19
    åĪĿæŃ¥
    0.17
     пÑĢедваÑĢ
    0.16
     prior
    0.16
     prelim
    0.16
    é¢ĦåħĪ
    0.15
     prelimin
    0.15
     Prel
    0.15
    before
    0.14
    é¢Ħä¹ł
    0.14
    Activations Density 0.612%

    No Known Activations