© 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. 46182
    Prev
    Next
    INDEX
    Explanations

    ganglion cells or nucleus

    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
     maxLength
    -0.06
    æĺİçģ«
    -0.06
    ä¹IJä¸ļ
    -0.06
     Äijáy
    -0.06
    iaz
    -0.06
    æīĢåľ¨åįķä½į
    -0.06
    Harness
    -0.06
     Zar
    -0.06
    åĮºåŁŁåĨħ
    -0.06
    itime
    -0.06
    POSITIVE LOGITS
    uxt
    0.08
    çĴIJ
    0.08
    Filtered
    0.08
    IDS
    0.08
     ÑħÑĢÑĥ
    0.08
    occhi
    0.08
     Cristal
    0.08
     bounced
    0.07
    filtered
    0.07
    pping
    0.07
    Activations Density 0.030%

    No Known Activations