© 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. 14628
    Prev
    Next
    INDEX
    Explanations

    mathematical notation symbols

    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
    ä
    -0.07
    äd
    -0.06
    æį¢
    -0.05
    ä¹ĭäºİ
    -0.05
    æĹłæīĢ
    -0.05
    -
    -0.05
    åĴ
    -0.05
    ä¸ĭè¿°
    -0.05
    j
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    ìŀ¥ìĿĢ
    0.10
    urale
    0.09
    icité
    0.09
    åħ¬åı¸æĺ¯
    0.08
    å¾·åĪ©
    0.08
    otton
    0.08
     ::=
    0.08
    ãĤ¹ãģ¯
    0.08
    ç³»ç»Łæĺ¯
    0.08
    èĮĥ
    0.08
    Activations Density 0.011%

    No Known Activations