© 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. 62680
    Prev
    Next
    INDEX
    Explanations

    code delimiters and output formatting

    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
    weiler
    -0.09
    åľ¨ä»Ĭ
    -0.08
    urn
    -0.08
    quita
    -0.08
    «
    -0.08
    ptest
    -0.08
    iquement
    -0.08
    èĢĺ
    -0.08
    ically
    -0.07
    ãģĭãģ¨
    -0.07
    POSITIVE LOGITS
    à¥įस
    0.08
    sid
    0.07
    åĴĮ
    0.07
    ed
    0.07
    esn
    0.07
    onstr
    0.07
    edig
    0.07
    amp
    0.07
    ness
    0.07
    æ·ĭæ¼ĵ
    0.07
    Activations Density 0.011%

    No Known Activations