© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    what is this identification

    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
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
    æĬ¬
    -0.08
    ä½ķæŶ
    -0.08
    æ°´å¹³
    -0.08
    æ¸ħéĨĴ
    -0.08
    ihan
    -0.07
     Infinite
    -0.07
    ä½ķæĻĤ
    -0.07
    è§Ħå®ļçļĦ
    -0.07
     Maur
    -0.07
    POSITIVE LOGITS
     clues
    0.09
    ystery
    0.08
    线索
    0.08
     зага
    0.08
    å¾Īåı¯èĥ½æĺ¯
    0.07
     Reconstruction
    0.07
     mystery
    0.07
     clue
    0.07
     spectro
    0.07
     reconstruction
    0.07
    Activations Density 0.091%

    No Known Activations