© 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. 50569
    Prev
    Next
    INDEX
    Explanations

    excitatory or inhibitory effects

    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
    çħ§
    -0.08
    ç½Ĺå¾·
    -0.08
     intimately
    -0.07
    ä½ĥ
    -0.07
    ellas
    -0.07
     Goed
    -0.07
    iless
    -0.07
    roda
    -0.07
    Å©
    -0.07
    æİĮæı¡çļĦ
    -0.06
    POSITIVE LOGITS
    æĹłè®ºä»İ
    0.08
    æĹłè®ºæĺ¯åľ¨
    0.08
    å¢ŀåĬł
    0.07
    éĻįèĢĹ
    0.07
    اÙģ
    0.07
     ÙĪزÙĬادة
    0.07
    Decre
    0.07
     netto
    0.07
    ngthen
    0.07
     increase
    0.07
    Activations Density 0.014%

    No Known Activations