© 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. 11992
    Prev
    Next
    INDEX
    Explanations

    suppression of

    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
    rvine
    -0.10
    ually
    -0.09
    uality
    -0.09
    swith
    -0.09
    Ĭ
    -0.08
    itura
    -0.08
    heu
    -0.08
    Å¡et
    -0.08
    ë¹ĦìĬ¤
    -0.08
    uate
    -0.08
    POSITIVE LOGITS
    es
    0.10
    ä¸įä½ıçļĦ
    0.08
    ively
    0.08
    ive
    0.08
    /en
    0.07
    äºĨ
    0.07
    uous
    0.07
    Ùĩ
    0.07
    iori
    0.07
    çĦ¶å¤§
    0.07
    Activations Density 0.038%

    No Known Activations