© 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. 31305
    Prev
    Next
    INDEX
    Explanations

    long duration

    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
    çŀ¬éĸĵ
    -0.08
    çļĦçŀ¬éĹ´
    -0.08
    VERTISE
    -0.08
    خت
    -0.08
    æ¯ıç§Ĵ
    -0.08
    åį³æĻĤ
    -0.08
    гоÑĤа
    -0.08
     unbiased
    -0.08
     dispens
    -0.08
    ajos
    -0.08
    POSITIVE LOGITS
     persistent
    0.11
    ä¹ħ
    0.11
     persistence
    0.10
    persistent
    0.10
    é¡½åĽº
    0.10
    åıįå¤įåıijä½ľ
    0.10
    æ£ĺæīĭ
    0.09
    Persistent
    0.09
     Persistent
    0.09
    ä¹ħäºĨ
    0.09
    Activations Density 0.074%

    No Known Activations