© 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. 32750
    Prev
    Next
    INDEX
    Explanations

    don't want

    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
    yan
    -0.08
    .getActive
    -0.07
    æ´»èºį
    -0.07
    åĩºä¸Ģçīĩ
    -0.07
    oses
    -0.07
    soon
    -0.07
     ÙĦÙĦÙħر
    -0.07
    IAS
    -0.07
    yor
    -0.07
    ytt
    -0.07
    POSITIVE LOGITS
     prescribed
    0.07
    æĹ¢
    0.07
     Ngo
    0.06
    impin
    0.06
     prescription
    0.06
    æ²»çĸĹæķĪæŀľ
    0.06
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.06
    æķ¢
    0.06
    离åIJĪ
    0.06
    åĽłä¸ºè¿Ļ个
    0.06
    Activations Density 0.002%

    No Known Activations