© 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. 9590
    Prev
    Next
    INDEX
    Explanations

    solution to equations

    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
    erio
    -0.08
    کز
    -0.08
    æľĢåīį沿
    -0.08
    aris
    -0.07
    æľĢåħĪè¿ĽçļĦ
    -0.07
    ائ
    -0.07
    èĢ³è¾¹
    -0.07
    åı¤éģĵ
    -0.07
    arang
    -0.07
    è´®
    -0.07
    POSITIVE LOGITS
    ëĭ´
    0.07
    ãĤĵ
    0.07
    èĬ½
    0.07
    TK
    0.06
    à¸Ĺี
    0.06
     simulation
    0.06
    åİļ
    0.06
    _schema
    0.06
    okal
    0.06
    SIM
    0.06
    Activations Density 0.031%

    No Known Activations