© 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. 40341
    Prev
    Next
    INDEX
    Explanations

    various types

    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
    abo
    -0.08
    uil
    -0.07
    æĹ¥ä¸Ĭ
    -0.07
    ænd
    -0.07
    ãĤīãģĹ
    -0.07
     stuff
    -0.07
    inn
    -0.07
    yss
    -0.06
    åĮ
    -0.06
    inna
    -0.06
    POSITIVE LOGITS
    两ç§įæĸ¹å¼ı
    0.12
    çŃīæĸ¹å¼ı
    0.12
    çŃīæīĭ段
    0.10
    åħ¶ä»ĸæĸ¹å¼ı
    0.10
    çŃīå½¢å¼ı
    0.09
    ãģĦãģļãĤĮ
    0.09
    è¿Ļ两ç§į
    0.09
    两ç§į
    0.09
    çŃīæĸ¹æ³ķ
    0.08
    çŃīå¤ļç§į
    0.08
    Activations Density 0.279%

    No Known Activations