© 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. 25020
    Prev
    Next
    INDEX
    Explanations

    percentages or small numbers

    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
    holders
    -0.07
    :///
    -0.07
    +")
    -0.07
    .future
    -0.07
    ина
    -0.07
    wege
    -0.06
    举éģĵ
    -0.06
    -enable
    -0.06
    ÙĪائ
    -0.06
    _detail
    -0.06
    POSITIVE LOGITS
    amy
    0.07
    èĩ
    0.07
    Fore
    0.07
    大æĸ¹
    0.07
    fore
    0.07
    ç²Ĺ
    0.06
     Giunta
    0.06
    abaj
    0.06
    å¤ķ
    0.06
    .FileSystem
    0.06
    Activations Density 0.160%

    No Known Activations