© 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. 46595
    Prev
    Next
    INDEX
    Explanations

    phrase/clause enclosed in parentheses

    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
    enet
    -0.07
    &w
    -0.07
    ä¹Łæĺ¯åĽłä¸º
    -0.07
    )&&
    -0.07
    æı½
    -0.07
    casts
    -0.07
    annes
    -0.07
     bela
    -0.07
    intValue
    -0.07
    arto
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.10
    åıĪåı«
    0.09
    åıĪåIJį
    0.09
    æĮĩçļĦ
    0.09
    åıĪ称
    0.09
    tock
    0.09
    Ìģ
    0.09
    æĺ¯ä¸Ģ个
    0.09
    æĺ¯æĮĩ
    0.08
    æĺ¯ä¸Ģéģĵ
    0.08
    Activations Density 2.000%

    No Known Activations