© 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. 65170
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and notation

    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
    à¹Ĥà¸ī
    -0.08
     crystal
    -0.07
    enor
    -0.06
    çĶŁæķĪåIJİ
    -0.06
    adt
    -0.06
    éĺħ读åħ¨æĸĩ
    -0.06
    ipa
    -0.06
    æģ°
    -0.06
    önt
    -0.06
    ele
    -0.06
    POSITIVE LOGITS
    èĢ³è¾¹
    0.08
     near
    0.07
    .keywords
    0.07
    èĢĮéĿŀ
    0.07
    æİ¥è¿ij
    0.07
     mendekati
    0.07
    ä¸įç»ı
    0.07
     Commentaires
    0.07
    æĸ¹åIJijåıijå±ķ
    0.07
    ctime
    0.07
    Activations Density 0.002%

    No Known Activations