© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    i.i.d. random walks and jumps

    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
     commanding
    -0.07
    èĻ«å®³
    -0.07
    оÑģÑĥ
    -0.07
     tún
    -0.07
     zones
    -0.07
    æĹłæķĮ
    -0.06
    idez
    -0.06
    çĽ¸æľĽ
    -0.06
     пеÑĢÑģо
    -0.06
    ans
    -0.06
    POSITIVE LOGITS
    ardia
    0.09
    éļıæľº
    0.08
    ipa
    0.08
     cari
    0.07
     ìłģ
    0.07
    sville
    0.07
    ardi
    0.07
    è°±
    0.07
    çļĦä¸Ģèĩ´
    0.07
    åĿĩåĢ¼
    0.07
    Activations Density 0.008%

    No Known Activations