© 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. 48403
    Prev
    Next
    INDEX
    Explanations

    wondered whether

    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
    å¦ĤæѤ
    -0.07
    çĽĺéĶ¦
    -0.06
    对è¿ĻäºĽ
    -0.06
    åı¯èĥ½å¯¹
    -0.06
     plugged
    -0.06
    cik
    -0.06
    èĪŀæĽ²
    -0.06
    åįļ士çĶŁå¯¼å¸Ī
    -0.06
    çŃ¹å»º
    -0.06
    åı¯èĥ½ä¼ļ对
    -0.06
    POSITIVE LOGITS
    sut
    0.08
    ç¡®
    0.08
    æŀľçĦ¶
    0.08
    isme
    0.08
    ãĤĪãģı
    0.08
    istine
    0.08
     earthly
    0.07
    omag
    0.07
    ç¡®å®ŀæĺ¯
    0.07
    代夫
    0.07
    Activations Density 0.091%

    No Known Activations