© 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. 62709
    Prev
    Next
    INDEX
    Explanations

    presenting provided shown

    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
    åIJİ天
    -0.08
    ä¼ĺèĥľ
    -0.07
    åİŁåĪĻä¸Ĭ
    -0.07
    ady
    -0.07
    æľīéĻIJçļĦ
    -0.06
     principles
    -0.06
    ä¸Ģæİ¢
    -0.06
    æ±ĩéĽĨäºĨ
    -0.06
    rell
    -0.06
    æľīéĻIJ
    -0.06
    POSITIVE LOGITS
     kèm
    0.09
    _FMT
    0.08
     accompanied
    0.08
     alongside
    0.08
     decimal
    0.08
     rounded
    0.07
    ä¸įæĸ¹ä¾¿
    0.07
    æį¢ç®Ĺ
    0.07
    æĸ¹ä¾¿
    0.07
     totals
    0.07
    Activations Density 0.033%

    No Known Activations