© 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. 39543
    Prev
    Next
    INDEX
    Explanations

    exceptions, conditions, or exceptions apply

    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
    åĬ¨è¾Ħ
    -0.07
    æĹłè®ºæĺ¯
    -0.07
    ä¸Ģ次åıĪä¸Ģ次
    -0.07
    ë¿IJë§Į
    -0.07
    è¶Ĭæĺ¯
    -0.07
    èĩªçĦ¶èĢĮçĦ¶
    -0.07
     totiž
    -0.07
     thereby
    -0.07
    å¿ħçĦ¶
    -0.07
    å°½æĶ¶
    -0.07
    POSITIVE LOGITS
    æľīæīĢ
    0.08
    éĹ®ä¸Ģä¸ĭ
    0.08
    ç£IJ
    0.08
    çī¹æ®ĬæĥħåĨµ
    0.07
    .Transactional
    0.07
    ixo
    0.07
    äum
    0.07
    å°ijéĩı
    0.07
    ä¸¥æł¼æĮī
    0.07
    developers
    0.07
    Activations Density 0.051%

    No Known Activations