© 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. 44035
    Prev
    Next
    INDEX
    Explanations

    or, and, /

    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
    è¦ģä¹Īæĺ¯
    -0.09
     Ø¥Ùħا
    -0.07
    _ASSIGN
    -0.07
    大家éĥ½å¾Ī
    -0.07
    è¦ģä¹Ī
    -0.07
    >Action
    -0.07
    ÑģÑģа
    -0.07
     entweder
    -0.07
    assist
    -0.07
    èĻ±
    -0.06
    POSITIVE LOGITS
    ients
    0.07
     вообÑīе
    0.07
    å°ĨæĿ¥çļĦ
    0.07
    æĢ§çŃī
    0.07
    éĥ½åĴĮ
    0.07
    æĺİäºĨ
    0.07
     dokonce
    0.07
    çĶļèĩ³åľ¨
    0.07
    å¹²èĦĨ
    0.07
     etc
    0.06
    Activations Density 0.240%

    No Known Activations