© 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. 43246
    Prev
    Next
    INDEX
    Explanations

    corporation

    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
    enius
    -0.08
     ↵            ↵
    -0.08
    ád
    -0.07
    并ä¸Ķè¿ĺ
    -0.07
    клей
    -0.07
    _sentence
    -0.07
     )))
    -0.07
     ↵        ↵
    -0.07
    apon
    -0.07
    EditMode
    -0.07
    POSITIVE LOGITS
    æľīä¸ĭåĪĹ
    0.07
    ä¸ĭåIJĮ
    0.06
    arel
    0.06
    ä¸įæĶ¾å¼ĥ
    0.06
    STDOUT
    0.06
     lim
    0.06
     Ther
    0.06
    irian
    0.06
    adero
    0.06
    ×ij׾
    0.05
    Activations Density 0.731%

    No Known Activations