© 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. 32284
    Prev
    Next
    INDEX
    Explanations

    structure definitions or configurations

    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
    Site
    -0.07
    ãĤ«ãĤ¿
    -0.07
    çĶµè¯ĿèģĶç³»
    -0.07
    æł¸
    -0.06
     corrected
    -0.06
    pond
    -0.06
    æ»´æ»´
    -0.06
    žÃŃ
    -0.06
    deb
    -0.06
    ook
    -0.06
    POSITIVE LOGITS
     subsection
    0.10
    çļĦåŃIJ
    0.10
    nested
    0.09
    åŃIJ
    0.08
    optgroup
    0.08
     nested
    0.08
    åµĮå¥Ĺ
    0.08
    åĪĨåĩº
    0.08
    $sub
    0.08
    erals
    0.07
    Activations Density 0.196%

    No Known Activations