© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33547
    Prev
    Next
    INDEX
    Explanations

    section and id markers

    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
    æ¨
    -0.08
     Ø«ÙĨا
    -0.08
     prol
    -0.07
    NAL
    -0.07
    å¹»
    -0.07
    ihan
    -0.07
    æ§Ľ
    -0.07
    ahoo
    -0.07
    nal
    -0.07
    失败
    -0.07
    POSITIVE LOGITS
    ãģ¯ãĤĦ
    0.07
    å¾Ģ
    0.07
     disku
    0.07
    tea
    0.06
    å¾Ģä¸Ĭ
    0.06
     ?>>
    0.06
    /><
    0.06
    dessen
    0.06
    quite
    0.06
    breadcrumbs
    0.06
    Activations Density 0.047%

    No Known Activations