© 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. 16979
    Prev
    Next
    INDEX
    Explanations

    deep/profound descriptions

    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
    baugh
    -0.09
    大åĪ©
    -0.09
    zada
    -0.09
    erÃŃa
    -0.09
    ÑĢад
    -0.09
    irian
    -0.09
    NCY
    -0.09
    ä¸įæīĵ
    -0.09
    vrier
    -0.09
    psilon
    -0.09
    POSITIVE LOGITS
     understanding
    0.08
    æ´ŀ
    0.07
    -
    0.06
    ening
    0.06
    erv
    0.06
    çIJĨ解
    0.06
    end
    0.06
    ,
    0.06
     Understanding
    0.06
    i
    0.06
    Activations Density 0.010%

    No Known Activations