© 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. 18565
    Prev
    Next
    INDEX
    Explanations

    date / posted in / comments off

    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
    ight
    -0.08
    ÑģÑĤÑĢÑı
    -0.07
    uret
    -0.07
    arcz
    -0.06
    imony
    -0.06
    æĹ¢
    -0.06
    æĹ¢ä¸į
    -0.06
    æĪIJåĬŁäºĨ
    -0.06
    æ®Ĩå°½
    -0.06
    ypse
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.17
    çĦ¶æĺ¯
    0.14
    ãĢħãģ®
    0.13
    ä¹ĭåıĪ
    0.12
    çŁ¥çļĦ
    0.12
    ãĢħ
    0.12
    à¹Ĩ
    0.11
     à¹Ĩ
    0.10
    åĿĢ
    0.10
    æѤä¸Ģ
    0.10
    Activations Density 0.012%

    No Known Activations