© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30824
    Prev
    Next
    INDEX
    Explanations

    longitudinal variations

    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
    intosh
    -0.08
    plier
    -0.07
    ẻ
    -0.07
    keley
    -0.07
    ristol
    -0.07
    ëŁ¼íĶĦ
    -0.07
    itecture
    -0.07
    eté
    -0.07
    สิà¹īà¸Ļ
    -0.07
    çı
    -0.07
    POSITIVE LOGITS
    åį³éĢĿ
    0.10
    oppable
    0.08
    æīĢåij¨
    0.08
    ebra
    0.08
    åħ¶äºĭ
    0.08
    raph
    0.08
    raphics
    0.07
    ê°ĢëĿ½
    0.07
    ادÙħ
    0.07
    çĻ¾å·Ŀ
    0.07
    Activations Density 0.011%

    No Known Activations