© 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. 13074
    Prev
    Next
    INDEX
    Explanations

    what is it asked

    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
    enhagen
    -0.07
    <dyn
    -0.07
    iggs
    -0.07
    åīįè¿°
    -0.07
    é¢ĺ为
    -0.07
    æĪĸ许æľī
    -0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.07
    类似éĹ®é¢ĺ
    -0.06
     elsewhere
    -0.06
    è¿Ļä¸ĢåĪĩ
    -0.06
    POSITIVE LOGITS
    çī¹çĤ¹åĴĮ
    0.08
    æľīåĵª
    0.08
    åĪĨåĪ«åľ¨
    0.08
    主è¦ģåĮħæĭ¬
    0.07
    æľĢæĸ°åıijå¸ĥ
    0.07
    并举
    0.07
    puts
    0.07
    hari
    0.07
    ifest
    0.07
    çķ
    0.07
    Activations Density 0.019%

    No Known Activations