© 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. 40548
    Prev
    Next
    INDEX
    Explanations

    questions about math or definitions

    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
     einf
    -0.08
    Pose
    -0.08
    åľĥ
    -0.07
    omin
    -0.07
    æľīéĴĪ对æĢ§åľ°
    -0.07
    δά
    -0.07
    ä¹ĭ缮çļĦ
    -0.07
    ¹Ħ
    -0.06
    çļĦ人类
    -0.06
    scriber
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºåľ¨
    0.08
    è¿Ļæĺ¯åĽłä¸º
    0.08
    åİŁåĽłæĺ¯
    0.08
    説
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
     Explanation
    0.07
    æĺ¯åħ·æľī
    0.07
    retty
    0.07
    çIJĨçĶ±æĺ¯
    0.06
     explanation
    0.06
    Activations Density 0.237%

    No Known Activations