© 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. 16451
    Prev
    Next
    INDEX
    Explanations

    titration and measurement

    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
    åĻª
    -0.08
    å¥¢æľĽ
    -0.08
    äºĶèĦı
    -0.07
    ä½ĵå¾ģ
    -0.07
    alten
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    ç¼Ĩ
    -0.07
    Denied
    -0.07
    shine
    -0.07
     PROFITS
    -0.07
    POSITIVE LOGITS
    æ»´å®ļ
    0.09
     tit
    0.09
     bure
    0.09
     aliqu
    0.08
     neutral
    0.08
     Verbrauch
    0.07
     calibrated
    0.07
    æłĩå®ļ
    0.07
     Tit
    0.07
    两æĶ¯
    0.07
    Activations Density 0.006%

    No Known Activations