© 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. 27169
    Prev
    Next
    INDEX
    Explanations

    website metadata and code structure

    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
     âĢ¦.
    -0.08
     (âĢ¦)
    -0.08
     »*
    -0.08
    âĢ¦the
    -0.08
    ká
    -0.08
     **«
    -0.07
    âĢ¦*
    -0.07
     dé
    -0.07
    âĢ¦**
    -0.07
    âĢ¦Â»
    -0.07
    POSITIVE LOGITS
    åįķ纯
    0.08
    åįķ纯çļĦ
    0.08
    èĢĥå¯Ł
    0.08
    æĻ®éĢļ
    0.07
    jiang
    0.07
     vivo
    0.07
    以ä¸Ĭ
    0.07
     Filed
    0.07
    æIJºå¸¦
    0.07
    åįķçĭ¬
    0.07
    Activations Density 0.010%

    No Known Activations