© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61948
    Prev
    Next
    INDEX
    Explanations

    time separator

    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
    icolor
    -0.07
    大æľī
    -0.06
    çĻ¾
    -0.06
    åĮĸçļĦ
    -0.06
    vens
    -0.06
    ç«ĭ
    -0.06
    ä¸į许
    -0.06
    åĢ¼ä¸º
    -0.06
    æ°
    -0.06
    æ¯ıåĪĨéĴŁ
    -0.06
    POSITIVE LOGITS
    añ
    0.09
     tù
    0.08
    odal
    0.08
    essor
    0.08
    ån
    0.08
    æĹłèĻij
    0.08
    .kr
    0.07
    æ±Łåİ¿
    0.07
    PMC
    0.07
    è¿Ļ个æŶåĢĻ
    0.07
    Activations Density 0.115%

    No Known Activations