© 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. 61519
    Prev
    Next
    INDEX
    Explanations

    account for or predict

    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
    è¶ħèĸĦ
    -0.08
    interop
    -0.08
    ãĨ
    -0.07
    å¿ħèĥľ
    -0.07
    fleisch
    -0.07
    chriften
    -0.07
    åİŁæĸĩéĵ¾æİ¥
    -0.07
    BSD
    -0.07
    æģ©æĸ¯
    -0.07
     ìĹĦ
    -0.07
    POSITIVE LOGITS
     attributable
    0.09
    ä¾ĥ
    0.07
     (%)
    0.07
     explained
    0.07
     cau
    0.07
    è´¡çĮ®
    0.07
    åįłæĢ»
    0.07
    èIJ½èIJ½
    0.07
    _contrib
    0.07
    lore
    0.07
    Activations Density 0.066%

    No Known Activations