© 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. 39473
    Prev
    Next
    INDEX
    Explanations

    consumption and use

    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
    sources
    -0.08
    (extra
    -0.07
    Distinct
    -0.07
     sources
    -0.07
    uddle
    -0.07
    orraine
    -0.07
    inou
    -0.07
    tia
    -0.07
     expectedResult
    -0.07
    ä¸Ĭå¸ĤçļĦ
    -0.07
    POSITIVE LOGITS
    æ¶ĪèĢĹ
    0.14
     consumption
    0.13
     depletion
    0.12
     Consumption
    0.11
     consumes
    0.11
    æ¶ĪèĢĹçļĦ
    0.11
     consum
    0.11
    èĢĹ
    0.10
     consume
    0.10
    æ¶Īè²»
    0.10
    Activations Density 0.147%

    No Known Activations