© 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. 23164
    Prev
    Next
    INDEX
    Explanations

    quoted content or phrases

    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
    áĥ¬
    -0.09
    æĿĪ
    -0.09
    кола
    -0.08
    ópolis
    -0.07
    åħ«è§Ĵ
    -0.07
    дÑĢе
    -0.07
    acce
    -0.07
    å°ıå¹³
    -0.07
    CAST
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    POSITIVE LOGITS
    ulich
    0.07
    anti
    0.06
     ra
    0.06
    onde
    0.06
    é¦ĸ
    0.06
    寻
    0.06
    дено
    0.06
    IRST
    0.06
    fit
    0.06
     Niel
    0.05
    Activations Density 0.090%

    No Known Activations