© 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. 32636
    Prev
    Next
    INDEX
    Explanations

    how extent rapidly

    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
    èī²åĪĹ
    -0.09
     supplement
    -0.08
    atetime
    -0.07
    chow
    -0.07
    对åŃ©åŃIJçļĦ
    -0.07
    å¯¹åĽ½å®¶
    -0.07
    对åIJĦ
    -0.07
    osz
    -0.07
    ãĥĥãĤ·ãĥ¥
    -0.07
    hov
    -0.07
    POSITIVE LOGITS
     specifically
    0.10
    uff
    0.09
     Specifically
    0.09
    åħ·ä½ĵ
    0.07
    åħ·ä½ĵçļĦ
    0.07
    åħ·ä½ĵæĿ¥è¯´
    0.07
     tepatnya
    0.07
     depending
    0.07
    çļĦç¨ĭ度
    0.07
    æķ£
    0.07
    Activations Density 0.077%

    No Known Activations