© 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. 43783
    Prev
    Next
    INDEX
    Explanations

    million shares or class

    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
    å²Ľ
    -0.07
    omb
    -0.06
    iya
    -0.06
    orama
    -0.06
    éª
    -0.06
    çħ¤
    -0.06
    ç«ł
    -0.06
     relative
    -0.06
     thr
    -0.06
    ap
    -0.06
    POSITIVE LOGITS
    æķ°éĩı为
    0.12
    lug
    0.10
    çļĦæķ°éĩı
    0.10
     sztuk
    0.10
    æĢ»æķ°çļĦ
    0.10
    è¿Ļæī¹
    0.10
    æķ¸éĩı
    0.10
    æķ°éĩıçļĦ
    0.09
    æķ°éĩıåĴĮ
    0.09
     Teixe
    0.09
    Activations Density 0.048%

    No Known Activations