© 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. 48817
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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
    é³Į
    -0.08
    chy
    -0.07
    fører
    -0.07
    avenport
    -0.07
    -0.07
    igare
    -0.07
    _OLD
    -0.07
    ¶
    -0.07
    éĥ½ä¸İ
    -0.06
    _running
    -0.06
    POSITIVE LOGITS
    ivel
    0.08
    RIA
    0.07
    anaf
    0.07
    essar
    0.07
    ÙĪÙħØ©
    0.07
    Bubble
    0.06
    ÙĪÙħÙĬ
    0.06
    ç¯ĩ
    0.06
    iore
    0.06
    èĭ¦è¾£
    0.06
    Activations Density 0.010%

    No Known Activations