© 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. 33664
    Prev
    Next
    INDEX
    Explanations

    verbs, microsurgical, ads, away, structural proteins, images, bowl games, major championships, network connection

    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
    ç¬Ļ
    -0.07
    ÑīÑĥ
    -0.07
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.07
    chie
    -0.07
    лÑĥÑĥ
    -0.06
    æŀ¶ç©º
    -0.06
    upro
    -0.06
    Xu
    -0.06
    ä»Ģä¹ĪéĹ®é¢ĺ
    -0.06
    åĪĪ
    -0.06
    POSITIVE LOGITS
    主è¦ģåĮħæĭ¬
    0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.09
    åĮħæĭ¬
    0.08
    åĨħ容åĮħæĭ¬
    0.08
    åIJĪ计
    0.07
    ":[{"
    0.07
    æĢ»è®¡
    0.07
    åħ±è®¡
    0.07
     including
    0.07
    éĻ¤äºĨåľ¨
    0.07
    Activations Density 0.045%

    No Known Activations