© 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. 30226
    Prev
    Next
    INDEX
    Explanations

    complete without

    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
    _again
    -0.07
    EX
    -0.07
     нен
    -0.06
    åħīèį£
    -0.06
    èĸ°
    -0.06
    YN
    -0.06
    æĹ¢èĥ½
    -0.06
    å¤ļåĸĿ
    -0.06
     عÙĪض
    -0.06
    opensource
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»åħĪ
    0.13
     prerequisite
    0.12
    çļĦåīįæıIJ
    0.12
    åīįæıIJæĺ¯
    0.10
    å¿ħé¡»è¦ģæľī
    0.10
    åīįæıIJ
    0.10
    离ä¸įå¼Ģ
    0.10
    æľªå®ĮæĪIJ
    0.10
     without
    0.09
     until
    0.09
    Activations Density 0.296%

    No Known Activations