© 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. 2607
    Prev
    Next
    INDEX
    Explanations

    Yes/no answers and 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
    arium
    -0.08
    Ĵáŀ
    -0.07
    å¼ĺ
    -0.06
    æģ¨ä¸įå¾Ĺ
    -0.06
     تÙĨا
    -0.06
    áĢ»
    -0.06
    omatic
    -0.06
     обл
    -0.06
    åĴ
    -0.06
    æĢ»ç»ĵå¦Ĥä¸ĭ
    -0.06
    POSITIVE LOGITS
    ÙĬض
    0.08
    æŃ£åĽł
    0.07
    iho
    0.07
    æĺ¯çļĦ
    0.07
     yes
    0.06
     nein
    0.06
    alha
    0.06
    ingat
    0.06
    Ø®ÙĬÙĨ
    0.06
    ãĥijãĥ¼ãĥĪ
    0.06
    Activations Density 0.014%

    No Known Activations