© 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. 23038
    Prev
    Next
    INDEX
    Explanations

    code blocks in programming

    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
    è¿Ľåİ»
    -0.07
    ä»ĸèĩªå·±
    -0.06
     whenever
    -0.06
    èĢĮåħ¶
    -0.06
    —if
    -0.06
     priem
    -0.06
    绽
    -0.06
    —in
    -0.06
    à¸Ŀาà¸ģ
    -0.06
    oppi
    -0.06
    POSITIVE LOGITS
    æĺ¯åIJ§
    0.08
    åĽ¾éī´
    0.08
    ebro
    0.08
    æŁIJä¸Ģ天
    0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    0.08
    возмо
    0.08
    å·¥åķĨ注åĨĮåı·
    0.07
    ihat
    0.07
     Burl
    0.07
    æŁIJ天
    0.07
    Activations Density 0.008%

    No Known Activations