© 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. 21992
    Prev
    Next
    INDEX
    Explanations

    words that explain or describe

    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
     rematch
    -0.08
    avin
    -0.08
     bersangkutan
    -0.07
    äºij顶
    -0.07
    èħĨ
    -0.07
    ooth
    -0.07
    Ñħай
    -0.07
    hav
    -0.07
     Matrix
    -0.07
     Solutions
    -0.07
    POSITIVE LOGITS
    æııåĨĻ
    0.10
    æıı
    0.10
    çĥĺæīĺ
    0.10
    æĻ¯çī©
    0.10
    åĪ»çĶ»
    0.09
    å¤¸å¼ł
    0.09
    æīĭæ³ķ
    0.09
    æııç»ĺ
    0.08
    æĬĴæĥħ
    0.08
    åĨĻæĻ¯
    0.08
    Activations Density 0.002%

    No Known Activations