© 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. 41771
    Prev
    Next
    INDEX
    Explanations

    fewer/less/more quantity

    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
    ãģ¨ãĤĤè¨Ģ
    -0.06
    enj
    -0.06
    мина
    -0.06
    ouc
    -0.06
     Hein
    -0.06
     Hann
    -0.06
    inen
    -0.06
    gy
    -0.06
    egov
    -0.06
    æıIJæĹ©
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸ
    0.08
    个人æĪĸ
    0.08
     appunto
    0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    0.08
    缴æİ¥æĪĸéĹ´æİ¥
    0.08
    ãģĤãĤĮãģ°
    0.07
    undes
    0.07
    åĵªæĢķ
    0.07
    å¤įåĪ¶æĪĸ
    0.07
    åĵªæĢķæĺ¯
    0.07
    Activations Density 0.113%

    No Known Activations