© 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. 24034
    Prev
    Next
    INDEX
    Explanations

    predicting, calculating, determining, converting

    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
    管çIJĨæľºåĪ¶
    -0.08
    _LOOP
    -0.07
    å¦ĤæѤä¹ĭ
    -0.07
    ssä
    -0.07
     somehow
    -0.07
    ÙĨØ´
    -0.07
    eppe
    -0.07
     maga
    -0.07
    åľ¨æŃ¤æ¬¡
    -0.07
     ì±ĦíĥĿ
    -0.07
    POSITIVE LOGITS
     anytime
    0.11
     whenever
    0.10
     predicting
    0.09
    é¢Ħæµĭ
    0.09
     лÑİбой
    0.09
     confidently
    0.09
     بÙħجرد
    0.09
     qualsiasi
    0.09
    计ç®Ĺ
    0.08
     ÙħتÙī
    0.08
    Activations Density 0.095%

    No Known Activations