© 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. 21304
    Prev
    Next
    INDEX
    Explanations

    automated process

    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
    ãĤĤãģĤãĤĬãģ¾ãģĻãģĮ
    -0.11
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.10
    ãģĤãĤĬãģ¾ãģĻãģĮ
    -0.09
    ä½Ĩæĺ¯åľ¨
    -0.09
    ä½Ĩåħ¶å®ŀ
    -0.09
    èĻ½çĦ¶åľ¨
    -0.09
    åĽºçĦ¶
    -0.09
     zwar
    -0.08
    èĻ½çĦ¶
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
     nonetheless
    0.11
    åĢ¼å¾Ĺä¸Ģ
    0.08
     anyway
    0.07
     ändå
    0.07
    åĢ¼å¾Ĺåħ³æ³¨
    0.07
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    0.07
    å°±æĺ¯äºĨ
    0.07
     nevertheless
    0.07
     anyhow
    0.07
     Bowman
    0.07
    Activations Density 0.132%

    No Known Activations