© 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. 47497
    Prev
    Next
    INDEX
    Explanations

    license following "the"

    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
    ium
    -0.07
    remen
    -0.06
    ington
    -0.06
    amar
    -0.06
     Romano
    -0.06
    raid
    -0.06
    Ùģات
    -0.06
    åĽłäººèĢĮå¼Ĥ
    -0.06
    indel
    -0.06
    å¸Ń
    -0.06
    POSITIVE LOGITS
    elves
    0.07
     mingle
    0.07
    ä¸ŃåĽ½åĽ½å®¶
    0.07
    æµ®
    0.07
    viz
    0.07
    è¨Ģ
    0.07
    akse
    0.07
     ''.
    0.07
    ä»ĸçļĦæīĭ
    0.07
    çĩŁ
    0.07
    Activations Density 0.006%

    No Known Activations