© 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. 26326
    Prev
    Next
    INDEX
    Explanations

    investigations and official actions

    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
    æĸ°éĹ»èĪĨæĥħ
    -0.07
    çĦī
    -0.07
    æĬķèµĦäºĭ件
    -0.07
    羣æŃ£æĪIJ为
    -0.07
     ÐŁÑĢезиденÑĤа
    -0.07
    æĢĿæĥ³ä¸Ĭ
    -0.07
    /from
    -0.07
    羣æŃ£åľ°
    -0.07
    å·¥åķĨè¡ĮæĶ¿
    -0.07
    ä¸ĭå²Ĺ
    -0.07
    POSITIVE LOGITS
     reportedly
    0.12
     allegedly
    0.11
     ÑıкобÑĭ
    0.10
    æѤåīį
    0.10
     (âĢ¦)
    0.10
     amid
    0.09
    âĸ½
    0.09
     بÙĦادÙĩ
    0.09
    ä»Ĭå¹´
    0.09
     [âĢ¦]
    0.09
    Activations Density 5.108%

    No Known Activations