© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14232
    Prev
    Next
    INDEX
    Explanations

    longer phrases, completion, or descriptions

    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
    MMC
    -0.07
    omio
    -0.07
     MMC
    -0.06
    ristol
    -0.06
    æļ
    -0.06
    ä¿Ŀ
    -0.06
     crystall
    -0.06
     acc
    -0.06
    ì°©
    -0.06
    ĭ
    -0.06
    POSITIVE LOGITS
    enom
    0.08
    ghi
    0.08
    Ñĥнк
    0.08
    AsyncResult
    0.08
    inkel
    0.08
    å¦Ĥä¸Ĭ
    0.08
    çŁ¥éģĵèĩªå·±çļĦ
    0.08
    ä¸įå·®
    0.07
    landes
    0.07
    åºķèĸª
    0.07
    Activations Density 0.001%

    No Known Activations