© 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. 49917
    Prev
    Next
    INDEX
    Explanations

    make sure that

    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
    ä½ķå¿ħ
    -0.08
    ÙĪØ·
    -0.07
     ag
    -0.07
    rita
    -0.07
    ernal
    -0.07
    å¿ħé¡»åĿļæĮģ
    -0.07
    ä¸įå¿ħ
    -0.07
    ala
    -0.07
    amba
    -0.07
    çİĭçİī
    -0.06
    POSITIVE LOGITS
    ãģĹãĤĤ
    0.09
    vrier
    0.07
    ).-
    0.07
    没è¿ĩ
    0.07
    UIL
    0.07
    æľīæĺİæĺ¾çļĦ
    0.07
    ÑĤеÑģÑĮ
    0.07
    ä¹Łåĸľæ¬¢
    0.07
    åIJĮåѦéĥ½
    0.07
    Ñıм
    0.07
    Activations Density 0.008%

    No Known Activations