© 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. 46383
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
    arren
    -0.08
    descr
    -0.07
    ductive
    -0.07
    ALLED
    -0.06
    okens
    -0.06
    opus
    -0.06
     vây
    -0.06
    ries
    -0.06
    åĮª
    -0.06
    åħ¶æ¬¡
    -0.06
    POSITIVE LOGITS
    è®¤è®¤çľŁçľŁ
    0.07
    baum
    0.07
    lek
    0.07
    خاÙĦ
    0.07
    åĴĮä¸Ń
    0.07
     thôi
    0.07
    ç¿ĺ
    0.07
    tiny
    0.07
    orno
    0.06
    åİ»ä¸ĸäºĨ
    0.06
    Activations Density 0.078%

    No Known Activations