© 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. 2850
    Prev
    Next
    INDEX
    Explanations

    subset inclusion containment

    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
    ä¸ĭéĿ¢æĺ¯
    -0.08
    egot
    -0.07
    .mongodb
    -0.07
     ÑĪÑĤÑĥк
    -0.07
    inga
    -0.07
     versa
    -0.06
    ansen
    -0.06
    |%
    -0.06
    ope
    -0.06
    brace
    -0.06
    POSITIVE LOGITS
     confines
    0.08
    otent
    0.08
    yan
    0.08
    æĪĸéĥ¨åĪĨ
    0.08
    ieux
    0.07
    اء
    0.07
    åįģæĹ¥
    0.07
     Morrow
    0.07
    ç¼
    0.07
    ä¸ī个æľĪ
    0.07
    Activations Density 0.004%

    No Known Activations