© 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. 16775
    Prev
    Next
    INDEX
    Explanations

    need to know

    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
    çħŀ
    -0.07
    æĦĪ
    -0.07
    æķ´
    -0.07
    缴æİ¥å°Ĩ
    -0.07
    第ä¸Ģçľ¼
    -0.07
    æ¯ı
    -0.06
    çłĶ究åıijçİ°
    -0.06
    èĽĽ
    -0.06
    æĮīçħ§è§Ħå®ļ
    -0.06
    çī¹æ´¾
    -0.06
    POSITIVE LOGITS
    æ³ĽæĮĩ
    0.09
    éĢļçĶ¨
    0.09
    æĺ¯åĽ½åĨħ
    0.09
    ¾
    0.09
    æĥ³å®ļ
    0.08
    éĢļçĶ¨çļĦ
    0.08
    éĿ¢åIJijåħ¨åĽ½
    0.08
     GENERIC
    0.08
    _STANDARD
    0.08
    BufferData
    0.08
    Activations Density 0.051%

    No Known Activations