© 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. 13919
    Prev
    Next
    INDEX
    Explanations

    recursive array 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
     Solid
    -0.07
    罡
    -0.07
    à¹Ģส
    -0.07
    ebb
    -0.07
    æİī
    -0.07
    åĽº
    -0.06
    pun
    -0.06
    左侧
    -0.06
    å·©åĽº
    -0.06
    ernet
    -0.06
    POSITIVE LOGITS
    第ä¸Ģ代
    0.12
    å¤ļ级
    0.12
    éĢIJ级
    0.11
     first
    0.11
    åįķå±Ĥ
    0.10
    [first
    0.10
     repeatedly
    0.10
    第ä¸Ģ次
    0.10
    å±Ĥå±Ĥ
    0.10
    第ä¸Ģè½®
    0.10
    Activations Density 0.103%

    No Known Activations