© 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. 41453
    Prev
    Next
    INDEX
    Explanations

    partial view

    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
    为åŃ¦æł¡
    -0.07
    aal
    -0.07
    对åŃ¦æł¡
    -0.07
    æŃ»ä¸į
    -0.07
    èĩªå·±çļĦè¡Į为
    -0.07
    ׼×Ļ
    -0.07
    éĿŀ常好
    -0.07
    çĶ±åİŁåijĬ
    -0.07
    åĴĮæķĻèĤ²
    -0.06
    çī¹åĪ«å¥½
    -0.06
    POSITIVE LOGITS
    çīĪ
    0.07
    .figure
    0.07
    ahrungs
    0.07
    æĢª
    0.07
    ä¸Ŀ
    0.07
    Alignment
    0.06
    n
    0.06
    ugel
    0.06
    åľ
    0.06
     laps
    0.06
    Activations Density 0.002%

    No Known Activations