© 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. 20849
    Prev
    Next
    INDEX
    Explanations

    XML attributes and values

    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
    raith
    -0.07
    天边
    -0.07
    ãĥģãĥ©
    -0.07
    bund
    -0.07
     Pagination
    -0.07
    举æĿ¯
    -0.07
    ¬ģ
    -0.07
    åħĪè¿Ľ
    -0.07
    èľ
    -0.07
    æĹłæ³ķ满足
    -0.07
    POSITIVE LOGITS
    æł¼å±Ģ
    0.10
     surrounding
    0.09
    åĽ´ç»ķ
    0.08
    主è¦ģ以
    0.08
    åĽ´ç»ķçĿĢ
    0.08
     окÑĢÑĥжа
    0.08
     Uniform
    0.07
    ilin
    0.07
    æĹ¥ä»¥
    0.07
    å»ĵ
    0.07
    Activations Density 0.009%

    No Known Activations