© 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. 61329
    Prev
    Next
    INDEX
    Explanations

    receptor

    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
    活水
    -0.07
    umpl
    -0.07
    авли
    -0.07
    åĴĮé¼ĵåĬ±
    -0.06
    RuleContext
    -0.06
    ialized
    -0.06
    大åĪ©
    -0.06
    thon
    -0.06
    产åĩº
    -0.06
    æµģçļĦ
    -0.06
    POSITIVE LOGITS
     receptors
    0.14
     receptor
    0.12
    åıĹä½ĵ
    0.10
     ÑĢеÑĨеп
    0.10
    æİ¥æĶ¶
    0.10
     Rezept
    0.09
    รัà¸ļ
    0.09
     ÙħستÙĤبÙĦ
    0.09
     receptive
    0.09
    éĿ¶
    0.09
    Activations Density 0.312%

    No Known Activations