© 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. 39120
    Prev
    Next
    INDEX
    Explanations

    parentheticals or qualifiers

    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
    omes
    -0.07
    å½ĵ羣
    -0.06
     doch
    -0.06
    äºĮ人çļĦ
    -0.06
    åı¯æĺ¯ä»ĸ
    -0.06
    δεÏĤ
    -0.06
    éĥ¡
    -0.06
    è¿Ļäºĭ
    -0.06
    ä¸įè¦ģåIJĥ
    -0.06
     Kear
    -0.06
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯åľ¨
    0.08
    argo
    0.08
    IMO
    0.08
    gré
    0.08
    æī¹
    0.07
    æĪĸèĢħ说
    0.07
     albeit
    0.07
    رÙĩا
    0.07
    å°¤åħ¶æĺ¯
    0.07
    isms
    0.07
    Activations Density 0.522%

    No Known Activations