© 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. 13116
    Prev
    Next
    INDEX
    Explanations

    SO.sub.2 generation

    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
    fullName
    -0.06
    å®ļåĬĽ
    -0.06
    å¹ħ
    -0.06
    究竣
    -0.06
    re
    -0.06
    prepend
    -0.06
    åŃ¦ä¹łä¸İ
    -0.06
     Taille
    -0.06
     discrim
    -0.06
    èĢĮä¸Ķæľī
    -0.06
    POSITIVE LOGITS
    [][
    0.08
     release
    0.08
    æ§Ľ
    0.08
    éĩĬæĶ¾åĩº
    0.08
     Released
    0.08
    Release
    0.08
     released
    0.08
    release
    0.08
    å¤ļä½Ļ
    0.08
    éĩĭåĩº
    0.07
    Activations Density 0.013%

    No Known Activations