© 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. 43114
    Prev
    Next
    INDEX
    Explanations

    numbers and place names

    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
    é«ĺ级ä¸ŃåѦ
    -0.09
    theon
    -0.08
    .setUp
    -0.08
    ROP
    -0.07
    çĦ¶æĺ¯
    -0.07
    à¹īาà¸ĩ
    -0.07
    omis
    -0.07
    æĮºèĥ¸
    -0.07
    доÑħ
    -0.07
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
    POSITIVE LOGITS
    çŁ¥
    0.08
    çĶļèĩ³äºİ
    0.07
    ä»ĸçĶļèĩ³
    0.07
    çĶļèĩ³
    0.07
    åĩĿ
    0.07
    æijĦ
    0.07
    æĴ®
    0.07
    çĶļèĩ³æĺ¯
    0.06
    çĶļèĩ³åľ¨
    0.06
    å¿ł
    0.06
    Activations Density 0.007%

    No Known Activations