© 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. 62378
    Prev
    Next
    INDEX
    Explanations

    code blocks and SQL statements

    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
    ing
    -0.06
    æīī
    -0.06
    ("")
    -0.06
    ä»ĸ表示
    -0.06
    edi
    -0.06
    =""
    -0.06
    ingi
    -0.06
     tr
    -0.06
    mey
    -0.06
    ละ
    -0.06
    POSITIVE LOGITS
    åĤ¬
    0.08
    åĪ°ä¸Ģèµ·
    0.07
    lord
    0.07
    azine
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    </think>
    0.07
    .");
    0.07
    tagen
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    ản
    0.07
    Activations Density 0.003%

    No Known Activations