© 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. 23116
    Prev
    Next
    INDEX
    Explanations

    MPL/2.0

    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
    轻轻ä¸Ģ
    -0.08
    èĶ¬èıľæ°´æŀľ
    -0.07
    essian
    -0.07
     ayrıca
    -0.07
    -package
    -0.07
     concer
    -0.07
     appunto
    -0.06
     Onze
    -0.06
    -tooltip
    -0.06
    :len
    -0.06
    POSITIVE LOGITS
     Huff
    0.07
    ừa
    0.06
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.06
    stv
    0.06
    azzi
    0.06
    akas
    0.06
    ä¸į好äºĨ
    0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸Ĺีà¹Ī
    0.06
     bè
    0.06
    está
    0.06
    Activations Density 2.959%

    No Known Activations