© 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. 56015
    Prev
    Next
    INDEX
    Explanations

    introduces definitions or statements

    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
    iba
    -0.08
    ConfigurationException
    -0.07
    ibs
    -0.07
    åŃIJåľ¨
    -0.07
    ä¹ĭåīįåľ¨
    -0.07
    人æīĢ
    -0.07
    åĩºçİ°åľ¨
    -0.06
    WithMany
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    IBA
    -0.06
    POSITIVE LOGITS
     à¤ĩसà¥ĩ
    0.09
    对æѤ
    0.08
    åħ¶ä¸º
    0.08
    è¿Ļæĸ¹éĿ¢
    0.07
     ìĿ´ë¥¼
    0.07
    ниÑĨ
    0.07
    å°Ĩåħ¶
    0.07
    umph
    0.07
     davon
    0.07
    è¿Ļæĸ¹éĿ¢çļĦ
    0.07
    Activations Density 0.204%

    No Known Activations