© 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. 34650
    Prev
    Next
    INDEX
    Explanations

    versus or separators

    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
    ansa
    -0.06
    elia
    -0.06
     individ
    -0.06
    tap
    -0.06
    bart
    -0.06
    ноÑģиÑĤÑģÑı
    -0.06
    æı¡
    -0.06
    plat
    -0.06
    ':"
    -0.06
    дÑĢÑĥ
    -0.06
    POSITIVE LOGITS
    à¸ľ
    0.08
    åħ±åIJĮåĬªåĬĽä¸ĭ
    0.08
    ToolStripMenuItem
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    äºĮåŃĹ
    0.07
     Pinh
    0.07
    ambe
    0.07
     PROG
    0.07
    idual
    0.07
    æī¹åĩĨçļĦé¡¹çĽ®
    0.07
    Activations Density 0.054%

    No Known Activations