© 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. 38088
    Prev
    Next
    INDEX
    Explanations

    internalization and absorption

    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
    áŁĦáŁĩ
    -0.07
    ekat
    -0.07
    anye
    -0.07
    éĩįçĶŁä¹ĭ
    -0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.07
    èĥ½è§ģ度
    -0.07
    uther
    -0.07
    acus
    -0.07
    lington
    -0.07
    æĸ°å±ĢéĿ¢
    -0.06
    POSITIVE LOGITS
    à¸Ŀัà¸ĩ
    0.08
    ä¸įä½ı
    0.08
    åĪ»éª¨éĵŃ
    0.08
    çī¢
    0.08
    oad
    0.08
    åĴĮåĨħ
    0.08
    åľ¨å¿ĥä¸Ń
    0.08
    æ¶ĪåĮĸåIJ¸æĶ¶
    0.08
    è¿ĩç¨ĭçļĦ
    0.07
    åĮĸçļĦ
    0.07
    Activations Density 0.025%

    No Known Activations