© 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. 61292
    Prev
    Next
    INDEX
    Explanations

    margin of error, statistics, population, median, range

    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
    orr
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    ä¸Ģå¦ĤæĹ¢å¾Ģåľ°
    -0.07
    OutputStream
    -0.07
    åijĹ
    -0.07
     möglichst
    -0.07
    ìĺ¬
    -0.07
    aksin
    -0.07
    ocode
    -0.07
    ecker
    -0.07
    POSITIVE LOGITS
     (~
    0.08
     (-
    0.08
    åįĬå¹´çļĦ
    0.08
     اÙĦباÙĦ
    0.07
     except
    0.07
    ä½łåį´
    0.07
    æ»
    0.06
     اÙĦباÙĦغ
    0.06
    åĢ¼ä¸º
    0.06
     Sos
    0.06
    Activations Density 0.020%

    No Known Activations