© 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. 56300
    Prev
    Next
    INDEX
    Explanations

    In base

    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
    онеÑĨ
    -0.07
    ä¹ĥèĩ³
    -0.07
    âĢ¦]
    -0.07
    boli
    -0.07
    Trivia
    -0.07
    æijĩæijĩ头
    -0.07
    éĿ©
    -0.07
    æłĩçļĦ
    -0.07
    AGING
    -0.07
    anzi
    -0.07
    POSITIVE LOGITS
    ais
    0.07
    æĭ³éģĵ
    0.07
    èĽ¾
    0.07
    ideon
    0.07
    æŃ£åĢ¼
    0.07
    西æŀĹ
    0.07
    çĻ¾åIJĪ
    0.07
    åºĶå½ĵä¾Ŀçħ§
    0.07
    æĮĩ导æĦıè§ģ
    0.07
    ena
    0.06
    Activations Density 0.004%

    No Known Activations