© 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. 26187
    Prev
    Next
    INDEX
    Explanations

    Barn Gallery

    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
    座
    -0.08
    è¬
    -0.07
    梦å¯IJ以æ±Ĥ
    -0.07
    éĽĦ
    -0.06
    å½¹
    -0.06
    ÃŃm
    -0.06
     دÙħ
    -0.06
    Æ
    -0.06
    uellement
    -0.06
    dbg
    -0.06
    POSITIVE LOGITS
    éĺ¿æ£®
    0.08
    оек
    0.08
    AsStream
    0.08
     menj
    0.07
    éĺ¿æĸ¯
    0.07
    éĢłåı¥
    0.07
    åħĢ
    0.07
    马æĸ¯
    0.07
    oins
    0.07
    rix
    0.07
    Activations Density 0.210%

    No Known Activations