© 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. 65515
    Prev
    Next
    INDEX
    Explanations

    after period, statement

    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
    ilh
    -0.08
    kest
    -0.08
    _refs
    -0.07
    çĶŁçī©å·¥ç¨ĭ
    -0.07
    सà¥ĩ
    -0.07
    éĽĨç»ĵåı·
    -0.07
    orst
    -0.07
    inol
    -0.07
    }{$
    -0.07
    áĢķáĢº
    -0.07
    POSITIVE LOGITS
    楷
    0.07
    INV
    0.07
    âĦ
    0.07
    æĦŁæĤŁ
    0.07
    мли
    0.06
    模仿
    0.06
    atoi
    0.06
     input
    0.06
    alais
    0.06
    ADI
    0.06
    Activations Density 0.006%

    No Known Activations