© 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. 15001
    Prev
    Next
    INDEX
    Explanations

    explaining or displaying code

    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
    ehend
    -0.08
    /of
    -0.08
    æľī人说
    -0.08
    人æĹł
    -0.08
    åı¯æ¢¦
    -0.08
    çĶ±åħ¶
    -0.07
    еÑĪÑĮÑģÑı
    -0.07
    å¾ĹæĪij
    -0.07
    æIJŃéħįä¸Ĭ
    -0.07
    æ³ķå®ļ
    -0.07
    POSITIVE LOGITS
    ioni
    0.07
    æĬĬè¿Ļ个
    0.07
    ä¸ĢäºĽ
    0.07
    ed
    0.07
    s
    0.07
    åĪĨæŀIJä¸Ģä¸ĭ
    0.07
    å¥ķ
    0.06
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    0.06
    æĺ¯å¤ļä¹Ī
    0.06
    atical
    0.06
    Activations Density 0.001%

    No Known Activations