© 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. 31434
    Prev
    Next
    INDEX
    Explanations

    function ...functionassociatesBell Labs

    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
    ignet
    -0.07
    ashi
    -0.07
    presse
    -0.07
     Burgos
    -0.07
    æ·¼
    -0.07
    ignan
    -0.07
    ERGE
    -0.07
     cred
    -0.06
    ostro
    -0.06
    æľīåĪ©çļĦ
    -0.06
    POSITIVE LOGITS
     ìłķ리
    0.07
    ÑĤоÑĩки
    0.07
    irsch
    0.07
     sche
    0.07
    лиÑģÑĤи
    0.06
     Klo
    0.06
    çĭ¼äºº
    0.06
    éĤ£äºĽå¹´
    0.06
     associates
    0.06
    åĴı
    0.06
    Activations Density 0.003%

    No Known Activations