© 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. 10783
    Prev
    Next
    INDEX
    Explanations

    works at

    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
    orias
    -0.07
    enstein
    -0.07
    erk
    -0.07
    %C
    -0.07
    //@
    -0.06
     breakout
    -0.06
    çĬ¯çļĦ
    -0.06
    знаÑĩ
    -0.06
    nez
    -0.06
    å´ĩ
    -0.06
    POSITIVE LOGITS
    ergia
    0.08
    REATE
    0.07
    inger
    0.07
    ä¸Ģè¾¹
    0.07
    为转载
    0.07
    èij©
    0.07
    æłĩ
    0.06
    ubar
    0.06
    ulled
    0.06
    ÒĽÑĭ
    0.06
    Activations Density 0.002%

    No Known Activations