© 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. 63001
    Prev
    Next
    INDEX
    Explanations

    occurred or ensued

    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
    izi
    -0.08
    åģļäºĭæĥħ
    -0.07
    çŁ¥åħ¶
    -0.07
    ä»Ģä¹Īéĥ½
    -0.06
    æĬĬä»ĸçļĦ
    -0.06
    estad
    -0.06
    تÙĬÙĨ
    -0.06
     داراÛĮ
    -0.06
    igno
    -0.06
    èĬ±éĥ½
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸ģิà¸Ķà¸Ĥึà¹īà¸Ļ
    0.10
     ensued
    0.09
     arise
    0.08
    ocking
    0.08
    é¼İé¼İ
    0.08
    ÙĩÙĪد
    0.08
     occur
    0.07
     entsteht
    0.07
    à¹ĥหà¹īà¸ģัà¸ļ
    0.07
    reten
    0.07
    Activations Density 0.555%

    No Known Activations