© 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. 33109
    Prev
    Next
    INDEX
    Explanations

    defining variables and functions

    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
    rost
    -0.07
    gian
    -0.07
    outine
    -0.07
     Virgin
    -0.07
    人称
    -0.06
    lator
    -0.06
    人ä¸ĸ
    -0.06
     ho
    -0.06
    ä¹į
    -0.06
    obot
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸ģร
    0.08
    æ³ģ
    0.07
     kif
    0.07
    é¶
    0.07
     manier
    0.07
    éĩı为
    0.07
    ãģĹãģ®
    0.07
    Pred
    0.07
    ufe
    0.07
     Canyon
    0.07
    Activations Density 0.001%

    No Known Activations