© 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. 30937
    Prev
    Next
    INDEX
    Explanations

    one of a kind

    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
    ¹
    -0.08
    ä¹Łä¸įçĶ¨
    -0.08
    amac
    -0.08
    wad
    -0.07
    è¿ĻäºĽè¯Ŀ
    -0.07
    words
    -0.07
    inks
    -0.07
    iscop
    -0.07
     equivalents
    -0.07
    γκ
    -0.07
    POSITIVE LOGITS
     ضÙħÙĨ
    0.09
     part
    0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
    ä¼Ĺå¤ļ
    0.08
     parmi
    0.08
    subset
    0.08
    åľ¨ä»¥
    0.07
    åľ¨åĨħçļĦ
    0.07
     subset
    0.07
    sq
    0.07
    Activations Density 0.157%

    No Known Activations