© 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. 56559
    Prev
    Next
    INDEX
    Explanations

    percentages involving numbers

    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
    åħ¨å¥Ĺ
    -0.07
    æ¿Ģ
    -0.07
    æ·»
    -0.06
    å°ijè§ģ
    -0.06
     sparing
    -0.06
    éļ¾å¿ĺ
    -0.06
    leta
    -0.06
    é¢ľ
    -0.06
    ç»ĪçĶŁ
    -0.06
    adian
    -0.06
    POSITIVE LOGITS
    åįłäºĨ
    0.11
    åįłæį®äºĨ
    0.09
     majority
    0.09
     ì°¨ì§Ģ
    0.08
    åįłåĪ°
    0.08
    åįłæľīçİĩ
    0.08
    ä¸»å¯¼åľ°ä½į
    0.08
     chiếm
    0.08
    åįłæ¯Ķ
    0.08
    åįłæį®
    0.08
    Activations Density 0.141%

    No Known Activations