© 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. 55552
    Prev
    Next
    INDEX
    Explanations

    vs or on followed by symbols or db terms

    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
    witz
    -0.07
    å¨ģå°Ķ
    -0.07
    onet
    -0.07
    å¸Ĥæĸ°
    -0.07
    çī¹æĸ°
    -0.07
    маÑĢа
    -0.07
    ÑĤоÑĩ
    -0.07
    ä»»åĬ³ä»»æĢ¨
    -0.07
    ató
    -0.07
    اظ
    -0.06
    POSITIVE LOGITS
    éĩıåĴĮ
    0.08
    éĩı为
    0.07
     Destination
    0.07
    abo
    0.07
    éĩı
    0.07
    wegen
    0.07
    å¥ĶåIJij
    0.07
    enberg
    0.06
    errick
    0.06
    Destination
    0.06
    Activations Density 0.003%

    No Known Activations