© 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. 47764
    Prev
    Next
    INDEX
    Explanations

    AV record breaking

    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
    į¼
    -0.09
    åĬłå¥½åıĭ
    -0.08
    erve
    -0.08
    åľ¨çº¿æŶéĹ´
    -0.08
     specta
    -0.08
    åĬłåħ¥ä¹¦çŃ¾
    -0.08
    请ä¸ĭè½½
    -0.07
    èģĮå®Ī
    -0.07
    çĤ¹åĩ»éĺħ读åİŁæĸĩ
    -0.07
    ij¸
    -0.07
    POSITIVE LOGITS
    æĩĤ
    0.08
    çŃĶ
    0.08
    åĽŀçŃĶ
    0.08
    æĩĤå¾Ĺ
    0.08
    解çŃĶ
    0.07
    aci
    0.07
    æĥ³è¦ģ
    0.06
    çĻ¾åº¦çŁ¥éģĵ
    0.06
    çļĦåĽŀçŃĶ
    0.06
    boss
    0.06
    Activations Density 0.009%

    No Known Activations