© 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. 29849
    Prev
    Next
    INDEX
    Explanations

    picking numbers probability

    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
    irat
    -0.07
    以大
    -0.06
    rz
    -0.06
    ª
    -0.06
    ping
    -0.06
    æķijåij½
    -0.06
    cko
    -0.06
    ä¸ĢåĮº
    -0.06
     Koh
    -0.06
     Inches
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°
    0.09
     poda
    0.08
    ãģĨãģ¡
    0.08
    æĢ»æķ°çļĦ
    0.08
    éĢļãĤĬ
    0.08
    شات
    0.08
    ÑģоÑĢ
    0.08
    åħ¶ä¸ŃåĮħæĭ¬
    0.08
    enumer
    0.08
    =count
    0.07
    Activations Density 0.016%

    No Known Activations