© 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. 42633
    Prev
    Next
    INDEX
    Explanations

    assume/suppose that

    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
     ÑģÑĥÑĤи
    -0.09
    eries
    -0.08
    èĢĮèµ°
    -0.08
    emus
    -0.08
    ï¸İ
    -0.08
    ients
    -0.08
    æĪijåIJĹ
    -0.08
    ãĥ¬ãĥĥ
    -0.07
    æľ¬è´¨
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæĿ¡ä»¶
    0.12
    æľī以ä¸ĭ
    0.08
    满足
    0.07
    tel
    0.07
    使å¾Ĺ
    0.07
    èĥ½å¤Łæ»¡è¶³
    0.07
    already
    0.07
    azer
    0.07
     sufficiently
    0.07
    äºĭåħĪ
    0.07
    Activations Density 0.028%

    No Known Activations