© 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. 50076
    Prev
    Next
    INDEX
    Explanations

    major divisions and categories

    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
    éĩĩ
    -0.07
    è¿Ľè¡Įè°ĥæŁ¥
    -0.07
    æĺİå¾·
    -0.07
    bacher
    -0.07
    ļĮ
    -0.07
    å¤ļæĸ¹éĿ¢
    -0.07
    combe
    -0.06
    æľīåħ³äºĭ项
    -0.06
    çĭ±
    -0.06
    ç¼¥
    -0.06
    POSITIVE LOGITS
    äºĶç§į
    0.10
    åħŃç§į
    0.10
    åĪĨåĪ«æĺ¯
    0.08
     namely
    0.08
    åħŃ大
    0.08
    ä¹ĭä¸ĢçļĦ
    0.08
     universally
    0.08
    äºĶ大
    0.08
    åĪĨåĪ¥æĺ¯
    0.08
     five
    0.08
    Activations Density 0.186%

    No Known Activations