© 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. 25652
    Prev
    Next
    INDEX
    Explanations

    explains or defines something

    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
    andex
    -0.08
    âĵĴ
    -0.08
     ï½¢
    -0.08
    CRET
    -0.08
    emps
    -0.08
    empa
    -0.07
    æĸ°éĥ½
    -0.07
    Fabr
    -0.07
    Eur
    -0.07
     juntas
    -0.07
    POSITIVE LOGITS
     usually
    0.07
    çľĭä½ł
    0.07
    oun
    0.07
     often
    0.07
     solito
    0.06
    usually
    0.06
    éĥ½è¦ģ
    0.06
    opsis
    0.06
    ê¶ģ
    0.06
     Usually
    0.06
    Activations Density 0.041%

    No Known Activations