© 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. 32400
    Prev
    Next
    INDEX
    Explanations

    besides / not only

    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
    æĽ´å¤ļ精彩
    -0.08
    èıģ
    -0.08
    ijken
    -0.07
    epage
    -0.07
    è¯ĨåĪ«åı·
    -0.07
    并ç»ı
    -0.07
    efeller
    -0.07
     ÐŁÐ¾ÐºÐ°Ð·Ð°
    -0.07
    ç½ijåıĭä¸Ĭä¼ł
    -0.07
    çĤ¹çĤ¹æ»´æ»´
    -0.07
    POSITIVE LOGITS
    odal
    0.08
     obvious
    0.07
    nyt
    0.07
    è¿Ļä¹Īç®Ģåįķ
    0.07
    以å¤ĸ
    0.07
    åŁºæľ¬çļĦ
    0.07
    æľ¬èº«çļĦ
    0.07
    éĻ¤æѤ
    0.07
    bei
    0.07
     Zav
    0.06
    Activations Density 0.181%

    No Known Activations