© 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. 42486
    Prev
    Next
    INDEX
    Explanations

    Client Kelly Richmond Url

    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
    ÑĬÑı
    -0.06
    /manual
    -0.06
    à¸ķามà¸ģà¸İหมาย
    -0.06
    /apt
    -0.06
    ä¸Ĭæī¬
    -0.06
    rape
    -0.06
    /add
    -0.06
    /Create
    -0.06
    eping
    -0.06
    ä¸Ģ度çļĦ
    -0.06
    POSITIVE LOGITS
    usada
    0.08
    arth
    0.08
    éģĵéģĵ
    0.08
    à¸Ļม
    0.07
    имо
    0.07
    ůst
    0.07
    isy
    0.07
    Äįky
    0.07
    åĨħå®¹è¿Ľè¡Į
    0.07
    æĪijåIJĹ
    0.07
    Activations Density 0.001%

    No Known Activations