© 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. 42229
    Prev
    Next
    INDEX
    Explanations

    code blocks or license headers

    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
    ↵
    -0.10
    otron
    -0.10
    åĬŁäºİ
    -0.09
    OfSize
    -0.08
    OperationException
    -0.08
    ók
    -0.08
    ÑĤÑĥÑĢи
    -0.08
    ersey
    -0.08
    ayette
    -0.08
    秫
    -0.08
    POSITIVE LOGITS
     ↵↵
    0.07
    çĦ¶èĢĮ
    0.06
    æѤå¤ĸ
    0.06
    e
    0.06
    è¿Ļæł·ä¸ĢæĿ¥
    0.06
    iy
    0.06
    尤为
    0.06
    m
    0.06
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.06
    ius
    0.06
    Activations Density 0.100%

    No Known Activations