© 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. 34054
    Prev
    Next
    INDEX
    Explanations

    being or is followed by description

    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
    chl
    -0.08
    amaz
    -0.07
    ARC
    -0.07
    yh
    -0.07
    ÏħÏĩ
    -0.07
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    -0.07
    马åı¯
    -0.07
    ogr
    -0.07
    arte
    -0.07
    maid
    -0.07
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.08
    æĪ¯
    0.07
    ÅĽle
    0.07
    éĵºå¤©çĽĸ
    0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.06
    기ëıĦ
    0.06
    æĿ¥ä¸´
    0.06
    enco
    0.06
    åĺĺ
    0.06
    å°±æĺ¯äºĨ
    0.06
    Activations Density 0.132%

    No Known Activations