© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    varying

    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
    ÃĵS
    -0.07
    è®°å½ķä¸ĭæĿ¥
    -0.07
    àªķà«į
    -0.07
    åĩłåıª
    -0.07
    æ²ģ
    -0.07
    TEMPL
    -0.07
    اÙĪر
    -0.07
    há
    -0.07
    æ³Į
    -0.07
    究åħ¶åİŁåĽł
    -0.07
    POSITIVE LOGITS
    ides
    0.07
    athe
    0.07
    idor
    0.07
     Avent
    0.07
    LineStyle
    0.07
    ints
    0.07
    owed
    0.07
    apura
    0.06
    çıĪ
    0.06
     avent
    0.06
    Activations Density 0.005%

    No Known Activations