© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64734
    Prev
    Next
    INDEX
    Explanations

    hidden or unknown

    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
    maj
    -0.07
    enni
    -0.07
    unny
    -0.07
    ç²Ĺ
    -0.07
    prob
    -0.07
    iki
    -0.07
    odos
    -0.07
     Commiss
    -0.07
    åĽº
    -0.06
     thô
    -0.06
    POSITIVE LOGITS
     unnoticed
    0.11
    åģĩ
    0.09
    ä»įçĦ¶åŃĺåľ¨
    0.09
    ä»įåŃĺåľ¨
    0.08
     invisible
    0.08
    ä»įåı¯
    0.08
    éļIJèĹıçļĦ
    0.08
     hidden
    0.08
     Hidden
    0.08
     silently
    0.08
    Activations Density 0.067%

    No Known Activations