© 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. 20790
    Prev
    Next
    INDEX
    Explanations

    recent past and time periods

    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
    uilt
    -0.08
    æŁĵ
    -0.07
     ple
    -0.07
    ضÙī
    -0.07
    åĴĮéĹ®é¢ĺ
    -0.06
    ipse
    -0.06
    ä¸įåIJ«
    -0.06
     custom
    -0.06
    èį·
    -0.06
    为ä»Ģä¹Īä¼ļ
    -0.06
    POSITIVE LOGITS
    åĩłæĹ¥
    0.08
    ếp
    0.07
     smack
    0.07
    ä¸įä¹ħçļĦ
    0.07
     (![
    0.07
    opp
    0.07
    è¿ijæľŁ
    0.07
     nearby
    0.07
    ä¸īéĩĮ
    0.07
    ÑĬв
    0.06
    Activations Density 0.349%

    No Known Activations