© 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. 29853
    Prev
    Next
    INDEX
    Explanations

    introducing subsequent terms

    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
    å¦ĤæŀľæĬĬ
    -0.07
     (?
    -0.07
    æī«
    -0.06
    åħĪæĺ¯
    -0.06
    ubah
    -0.06
    æĪªçĦ¶ä¸įåIJĮ
    -0.06
     gry
    -0.06
     Hunts
    -0.06
    ardin
    -0.06
    å¦Ĥæŀľä»ĸ们
    -0.06
    POSITIVE LOGITS
     tạm
    0.10
    æļĤå®ļ
    0.09
    åľ¨ä»¥åIJİ
    0.09
    继ç»Ń使çĶ¨
    0.09
    _accepted
    0.08
    íķĺê¸°ë¡ľ
    0.08
    æļĤæŶ
    0.08
    继ç»Ńåľ¨
    0.08
     thereafter
    0.08
    并使çĶ¨
    0.08
    Activations Density 0.044%

    No Known Activations