© 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. 38340
    Prev
    Next
    INDEX
    Explanations

    experimental data and crystal structures

    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
    ee
    -0.07
    åŀ¢
    -0.06
    å®
    -0.06
    é½IJåħ¨
    -0.06
     boh
    -0.06
    w
    -0.06
    era
    -0.06
    erval
    -0.06
    ä¸ĩèĥ½
    -0.06
    ÙĦÙĬÙħ
    -0.06
    POSITIVE LOGITS
    suite
    0.09
    æĥĬ天
    0.07
     pragma
    0.07
    ahu
    0.07
     suite
    0.07
    ató
    0.07
     junit
    0.07
    _suite
    0.07
    OwnerId
    0.07
    ainless
    0.07
    Activations Density 0.009%

    No Known Activations