© 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. 12631
    Prev
    Next
    INDEX
    Explanations

    played by

    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
    纬
    -0.08
    ionale
    -0.08
    èĥŀèĥİ
    -0.07
    ä¸įæĸŃåĬłå¤§
    -0.07
    ilion
    -0.07
    eos
    -0.07
    eo
    -0.07
    eam
    -0.07
    onos
    -0.07
     ×ij×ĺ
    -0.07
    POSITIVE LOGITS
    èł
    0.07
    åįķæĸ¹éĿ¢
    0.07
    åıªæľīä¸Ģ个
    0.07
    fest
    0.07
    andas
    0.07
    igrations
    0.07
    åįķ
    0.07
    è¨Ģ
    0.06
     allein
    0.06
    ayang
    0.06
    Activations Density 0.098%

    No Known Activations