© 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. 30704
    Prev
    Next
    INDEX
    Explanations

    title says

    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
    achu
    -0.08
    ç¬Ķ趣éĺģ
    -0.07
    TokenType
    -0.07
     designated
    -0.07
    çļĦä¸ĵæłı
    -0.07
    .disc
    -0.07
    éĥ¨é¦ĸ
    -0.07
     Dép
    -0.07
    é¢ĦæĸĻ
    -0.07
    æݨ移
    -0.07
    POSITIVE LOGITS
    åħ¨æĸĩ
    0.08
    stek
    0.07
    áĢĶáĢºáĢ¸
    0.07
    oise
    0.07
    Kick
    0.07
     ÑģÑİ
    0.07
     rewritten
    0.06
    arts
    0.06
    è¿Ħä»Ĭ
    0.06
     IDE
    0.06
    Activations Density 0.015%

    No Known Activations