© 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. 41281
    Prev
    Next
    INDEX
    Explanations

    domains and generators

    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
    å¼Ľ
    -0.08
    æľīä»·åĢ¼çļĦ
    -0.08
    sey
    -0.08
    äºĶ常
    -0.08
    uku
    -0.07
    é©°
    -0.07
    conte
    -0.07
     تعÙĦ
    -0.07
    æĶ¾è¿ĩ
    -0.07
    åı¯èĥ½æĢ§
    -0.07
    POSITIVE LOGITS
    patible
    0.08
    декваÑĤ
    0.07
    isir
    0.07
    ť
    0.07
    代表æĢ§çļĦ
    0.07
    æ¡
    0.07
    pell
    0.07
     Galler
    0.07
    å¾ĭå·±
    0.07
    ä»»
    0.07
    Activations Density 0.015%

    No Known Activations