© 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. 51337
    Prev
    Next
    INDEX
    Explanations

    horizontal separators

    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
     inexp
    -0.08
    leder
    -0.07
    lesc
    -0.07
    ÑħÑĢо
    -0.07
    urch
    -0.07
    aminer
    -0.07
    οÏį
    -0.07
    umo
    -0.07
    iegel
    -0.07
    åľ¨éĤ£éĩĮ
    -0.07
    POSITIVE LOGITS
    人以ä¸ĭ
    0.07
    KK
    0.06
     Patt
    0.06
    arán
    0.06
    åį«åĨķ
    0.06
    éİ®
    0.06
    aras
    0.06
    ä¸İçĶŁæ´»
    0.06
    Åijt
    0.06
    åĿļæĮģæĬĬ
    0.06
    Activations Density 0.043%

    No Known Activations