© 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. 10908
    Prev
    Next
    INDEX
    Explanations

    opening new possibilities

    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
    htub
    -0.08
    estern
    -0.07
    warts
    -0.07
    ä¹ĭæĢ¥
    -0.07
    plash
    -0.07
    åĢ¾åIJij
    -0.07
    念
    -0.07
    icus
    -0.07
    ä¸Ģ鸣
    -0.07
     ÙĪاÙĤ
    -0.07
    POSITIVE LOGITS
     possibilities
    0.17
     opportunities
    0.15
    æĭĵå±ķ
    0.14
     возможноÑģÑĤей
    0.14
    åı¯èĥ½æĢ§
    0.14
     Möglichkeiten
    0.13
    çļĦåı¯èĥ½æĢ§
    0.12
    åıijå±ķ空éĹ´
    0.12
     Opportunities
    0.12
     avenues
    0.12
    Activations Density 0.158%

    No Known Activations