© 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. 47933
    Prev
    Next
    INDEX
    Explanations

    citations (number followed by parenthesis)

    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
     comis
    -0.07
    æѤæŶçļĦ
    -0.07
    ardon
    -0.07
    ÑģлÑĥ
    -0.07
    认éĶĻ
    -0.07
    ЧС
    -0.07
    ambi
    -0.07
    kog
    -0.07
    çĽĪçĽĪ
    -0.07
    ibli
    -0.07
    POSITIVE LOGITS
    ç½ĹéĤ£
    0.09
    illot
    0.08
    å±ģèĤ¡
    0.07
    tou
    0.06
    æĿĥå¨ģ
    0.06
    æľ¨é½IJ
    0.06
    åįģåħ¨
    0.06
    edula
    0.06
     touched
    0.06
    伦
    0.06
    Activations Density 0.389%

    No Known Activations