© 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. 63166
    Prev
    Next
    INDEX
    Explanations

    relative risk (RR) values

    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
    oldt
    -0.08
    fare
    -0.08
    ]*(
    -0.08
    afia
    -0.08
    ÏĢÏī
    -0.07
    usra
    -0.07
    宿
    -0.07
    æijĨåľ¨
    -0.07
    çľĭæĿ¥
    -0.07
    翱
    -0.07
    POSITIVE LOGITS
    ictured
    0.07
     ÂŃ
    0.07
    ĻĤ
    0.07
    __;
    0.07
     PMID
    0.07
    %;
    0.07
    _;
    0.07
    omba
    0.06
     Figure
    0.06
    ä¸ĭ称
    0.06
    Activations Density 0.519%

    No Known Activations