© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44276
    Prev
    Next
    INDEX
    Explanations

    took

    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
    Negative Logits
    æıIJä¾ĽæĽ´
    -0.09
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    æıIJä¾ĽæĽ´åĬł
    -0.07
    è¿Ļä¹Ī说
    -0.06
    unte
    -0.06
    ä¸įå°ijäºİ
    -0.06
    æıIJä¾ĽæĽ´å¤ļçļĦ
    -0.06
    éf
    -0.06
    å±ĬæŶ
    -0.06
    çĶ±åħ¶
    -0.06
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.12
    ãģ¾ãģĽãĤĵãģ§ãģĹãģŁ
    0.10
     took
    0.10
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    0.10
     Took
    0.10
     jsem
    0.09
     myself
    0.09
     assumed
    0.09
     jsme
    0.09
     vardı
    0.09
    Activations Density 0.017%

    No Known Activations