© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2324
    Prev
    Next
    INDEX
    Explanations

    sentence termination punctuation

    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
     alternatively
    -0.08
     respectiv
    -0.08
     sempat
    -0.07
     ÑıкобÑĭ
    -0.07
     prelimin
    -0.07
    缮åīįå·²
    -0.07
    å®ŀéĻħä¸Ĭæĺ¯
    -0.07
     Belieb
    -0.07
    第ä¸Ģ次
    -0.07
    æł¹æį®å®ŀéĻħæĥħåĨµ
    -0.07
    POSITIVE LOGITS
    è¿Ļ个éģĵçIJĨ
    0.09
    ä¸į以
    0.09
    ãģĵãģĿ
    0.08
    è¿Ļæīįæĺ¯
    0.08
    åĽłæŃ¤åľ¨
    0.07
    è¿Ļè¯Ŀ
    0.07
    èĢĮè¿ĻäºĽ
    0.07
    è¿Ļä¸ĢçĤ¹
    0.07
    avid
    0.07
    ساد
    0.07
    Activations Density 0.554%

    No Known Activations