© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    encourage

    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
    aver
    -0.06
    ä¸įåıĬå¾ħ
    -0.06
    ä¸įçŁ¥éģĵä½ł
    -0.06
    éļĽ
    -0.06
    indel
    -0.06
    rending
    -0.06
     положение
    -0.06
    celli
    -0.06
     вÑĢе
    -0.06
    æĥĬå¿ĥåĬ¨
    -0.06
    POSITIVE LOGITS
    åĴĮè§ĦèĮĥ
    0.10
    åĴĮé¼ĵåĬ±
    0.10
    rypted
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    ayet
    0.09
     khÃŃch
    0.08
    sville
    0.08
    stå
    0.08
    åĴĮè¦ģæ±Ĥ
    0.08
    ype
    0.08
    Activations Density 0.023%

    No Known Activations