© 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. 47672
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    robe
    -0.07
    ulton
    -0.07
    isa
    -0.07
    大åĬĽå®ŀæĸ½
    -0.06
    éŨå¸Ĥ
    -0.06
    agua
    -0.06
    ç³ľ
    -0.06
    æľ¬æ³ķ
    -0.06
    <html
    -0.06
    عب
    -0.06
    POSITIVE LOGITS
    ØŁØŁ
    0.09
    å±ħçĦ¶æĺ¯
    0.09
    å±ħçĦ¶
    0.09
    ç«ŁçĦ¶
    0.08
    ï¼Ł
    0.08
    ï¼ģï¼Ł
    0.08
    parable
    0.08
    ?!
    0.08
    ç«ŁçĦ¶æĺ¯
    0.07
     ØŁ
    0.07
    Activations Density 0.068%

    No Known Activations