© 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. 50739
    Prev
    Next
    INDEX
    Explanations

    Perhaps followed by elaboration

    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
     basically
    -0.09
    sWith
    -0.09
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    -0.09
    opyright
    -0.09
    uÅŁ
    -0.09
     kemungkinan
    -0.09
    ÑĩаÑģÑĤли
    -0.08
     praticamente
    -0.08
    raven
    -0.08
    Äįko
    -0.08
    POSITIVE LOGITS
     saja
    0.11
    ãģĺãĤģ
    0.08
    ëį°ìļĶ
    0.08
    æľī人ä¼ļ
    0.08
    è¿Ļå°±æĺ¯
    0.08
     chÄĥng
    0.07
    -vous
    0.07
     there
    0.07
    ioned
    0.07
    ãģ£ãģįãĤĬ
    0.07
    Activations Density 0.016%

    No Known Activations