© 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. 16991
    Prev
    Next
    INDEX
    Explanations

    code snippets with specific keywords

    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
    menta
    -0.08
    лав
    -0.07
    aight
    -0.07
    ë¥
    -0.07
    rico
    -0.07
    éĹ®
    -0.07
    juje
    -0.07
    åļ¼
    -0.06
    éģĹçķĻ
    -0.06
    ;d
    -0.06
    POSITIVE LOGITS
    ILES
    0.07
    egas
    0.07
    soon
    0.06
    èĬĤåīį
    0.06
    etsy
    0.06
     <![
    0.06
    èī¯åĵģ
    0.06
     chÄĥng
    0.06
    ä¸į离
    0.06
    ison
    0.06
    Activations Density 0.158%

    No Known Activations