© 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. 39612
    Prev
    Next
    INDEX
    Explanations

    press kit, Twitter account, author, blogs, Bottom row, scroll

    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
     (âĢ¦)
    -0.12
    [âĢ¦
    -0.08
     [âĢ¦
    -0.08
    øv
    -0.07
    änen
    -0.07
    isman
    -0.07
     [âĢ¦]
    -0.07
    ajaan
    -0.07
    onomy
    -0.07
     FEMA
    -0.06
    POSITIVE LOGITS
    çļĦåįļ客
    0.07
    ãĥŃãĥ³ãĤ°
    0.07
    ä¸Ĭä¸Ģç«ł
    0.07
     katt
    0.07
    飽
    0.06
    ãĥ¬ãĥ¼ãĤ¶ãĥ¼
    0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.06
    é»ĥéĩij
    0.06
    èµĦæºIJæķ´åIJĪ
    0.06
    çİ¥
    0.06
    Activations Density 2.683%

    No Known Activations