© 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. 41002
    Prev
    Next
    INDEX
    Explanations

    previously designated

    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
    inho
    -0.06
    æ¯ıä¸Ģä½į
    -0.06
    è¿ĺæľīä¸ĢçĤ¹
    -0.06
    agir
    -0.06
     both
    -0.06
    è£ħåľ¨
    -0.06
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    -0.05
    imd
    -0.05
    æ¯ıä¸Ģ个人
    -0.05
    fdf
    -0.05
    POSITIVE LOGITS
    åĪĨç±»
    0.12
    åĮºåĪĨ
    0.10
    åĪĨé¡ŀ
    0.10
    åĩ¡
    0.10
    ä½Ĩåĩ¡
    0.10
     ë¶Ħë¥ĺ
    0.10
    åĮºåĪ«
    0.10
    产åĵģåĪĨç±»
    0.10
     classifications
    0.09
     distinction
    0.09
    Activations Density 0.221%

    No Known Activations