© 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. 60372
    Prev
    Next
    INDEX
    Explanations

    color octet, higher spins

    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
    å¼ı设计
    -0.07
    ä¸ĩ次
    -0.06
    æķ°çIJĨ
    -0.06
     biograf
    -0.06
    ä¸Ģ个女人
    -0.06
    aden
    -0.06
    èľķ
    -0.06
    ä¿¡çĶ¨
    -0.06
    alang
    -0.06
    ographical
    -0.06
    POSITIVE LOGITS
    arana
    0.08
    Å©
    0.08
    ingles
    0.08
    aranja
    0.08
    uevo
    0.08
    rosse
    0.07
    رة
    0.07
    ãĤ¸ãĤ§
    0.07
    egment
    0.07
    åĤ¢ä¼Ļ
    0.07
    Activations Density 0.003%

    No Known Activations