© 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. 51419
    Prev
    Next
    INDEX
    Explanations

    when needed or required

    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
     whoever
    -0.08
    avo
    -0.07
     who
    -0.07
     unless
    -0.07
    ofire
    -0.06
    abt
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
     whenever
    -0.06
     altogether
    -0.06
     somewhat
    -0.06
    POSITIVE LOGITS
    enen
    0.08
    /if
    0.08
    ãģ«å¿ľãģĺãģ¦
    0.07
    çIJ
    0.07
    åľ°åĮºåĴĮ
    0.07
    ä¸Ģæĸ°çļĦ
    0.07
    ä¸įå·®
    0.07
    /by
    0.07
    rog
    0.07
    è¾Ħ
    0.07
    Activations Density 0.051%

    No Known Activations