© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    many-to-many relations

    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
    缨
    -0.08
    óc
    -0.07
    duk
    -0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
    iday
    -0.07
    ä¼´éļı
    -0.07
    itage
    -0.07
    .handleError
    -0.07
    é¹°
    -0.07
    ADX
    -0.06
    POSITIVE LOGITS
    yser
    0.08
    agged
    0.07
    æĬ½è±¡
    0.07
    ืà¹Īà¸Ń
    0.07
     bip
    0.07
    å°Ħ
    0.07
    袴
    0.07
    orc
    0.07
    å°Ħç®Ń
    0.07
    Orm
    0.07
    Activations Density 0.006%

    No Known Activations