© 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. 58585
    Prev
    Next
    INDEX
    Explanations

    physical objects and their measurements

    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
    гне
    -0.07
    å¦ĥ
    -0.07
    à¹Ģà¸Ľà¹ĩà¸Ļสà¹Īวà¸Ļ
    -0.07
     epis
    -0.07
    иÑģи
    -0.06
     nomination
    -0.06
    Sink
    -0.06
    mane
    -0.06
     wÅĤaÅĽci
    -0.06
    äººä¸ºæľ¬
    -0.06
    POSITIVE LOGITS
    etary
    0.07
    ekten
    0.07
    çŃīé¢ĨåŁŁçļĦ
    0.07
    uru
    0.07
    лла
    0.07
     roulant
    0.07
    æĥ³ä¸įåĪ°
    0.07
    çŃīåľºæīĢ
    0.07
     astr
    0.07
    ynam
    0.07
    Activations Density 0.153%

    No Known Activations