© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17091
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms and descriptions

    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
    ’
    -0.08
     “
    -0.07
     plainly
    -0.07
     specs
    -0.07
    -0.07
    èĭ¥
    -0.07
     slated
    -0.07
     probably
    -0.06
     combos
    -0.06
    ‘
    -0.06
    POSITIVE LOGITS
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.12
    éļıçĿĢæŶéĹ´çļĦæݨ移
    0.12
    éļıçĿĢæŶéĹ´çļĦ
    0.11
    ä¹Łç§°ä¸º
    0.09
    å·²ç»ıè¾¾åĪ°äºĨ
    0.09
    æĽ´åĬłæ³¨éĩį
    0.09
    åıĺå¾ĹæĽ´åĬł
    0.09
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    0.09
    ä¿¡æģ¯ä»ħä¾ĽåıĤèĢĥ
    0.09
    åħ·æľīéĩįè¦ģçļĦ
    0.09
    Activations Density 0.001%

    No Known Activations