© 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. 45580
    Prev
    Next
    INDEX
    Explanations

    time stamps and index

    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
    ¿
    -0.07
    GetString
    -0.07
    TimeString
    -0.07
     Pom
    -0.07
    orthy
    -0.06
    åIJĮæĹ¶åľ¨
    -0.06
    enville
    -0.06
    æ¢ĵ
    -0.06
     identical
    -0.06
    uestion
    -0.06
    POSITIVE LOGITS
    è±ģçĦ¶
    0.08
    ìĸ¸
    0.08
    å¼Ħæ¸ħ
    0.08
    datal
    0.08
    npc
    0.07
     Dernière
    0.07
     datastore
    0.07
    nest
    0.07
    åį«åĨķ
    0.07
    yun
    0.07
    Activations Density 0.006%

    No Known Activations