© 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. 12218
    Prev
    Next
    INDEX
    Explanations

    decisions or approvals

    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
    ahu
    -0.07
    æĬ¥åIJįæŶ
    -0.06
    æ°¯ä¹Ļçĥ¯
    -0.06
    å¤©çľŁ
    -0.06
    åĪļä»İ
    -0.06
    åīĽ
    -0.06
    สุ
    -0.06
     corde
    -0.06
    夫åŃIJ
    -0.06
    为äºĨæĽ´å¥½çļĦ
    -0.06
    POSITIVE LOGITS
    ä¸įäºĪ
    0.10
    åıĹçIJĨ
    0.09
    çŃĶå¤į
    0.09
    åĩĨäºĪ
    0.09
    åĨ³å®ļæĺ¯åIJ¦
    0.09
    äºĪ以
    0.09
    åĨ³å®ļ
    0.09
    驳åĽŀ
    0.08
     issuing
    0.08
    åĽŀåºĶ
    0.08
    Activations Density 0.243%

    No Known Activations