© 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. 46133
    Prev
    Next
    INDEX
    Explanations

    exports

    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
    omia
    -0.06
    ÙĥÙĪ
    -0.06
    ucz
    -0.06
    è¾»
    -0.06
    vak
    -0.06
    å®Īæ³ķ
    -0.06
    ><![
    -0.06
     cov
    -0.05
    èĤ¥çļĤ
    -0.05
    æ±
    -0.05
    POSITIVE LOGITS
    ffffffff
    0.09
    æĢ¥æĢ¥
    0.08
    ĽĦ
    0.08
    -muted
    0.08
     miscellaneous
    0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    0.07
    lexport
    0.07
    ãĥ«ãĥī
    0.07
    asename
    0.07
    LOY
    0.07
    Activations Density 0.037%

    No Known Activations