© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    what can you expect?

    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
     ï¼Ī
    -0.07
    tbl
    -0.06
     prom
    -0.06
    tile
    -0.06
    ä¸įæĦ§
    -0.06
     “
    -0.06
    对ä»ĸçļĦ
    -0.06
    éĩij森
    -0.06
     ,
    -0.06
    /e
    -0.06
    POSITIVE LOGITS
    ãģĭãģ¨ãģĦãģĨãģ¨
    0.12
    çļĦåij¢
    0.11
    åij¢
    0.11
    åı¯æĥ³
    0.09
    äºĨåij¢
    0.08
    ë°Ķë¡ľ
    0.08
    æĺµ
    0.08
    ?>>
    0.08
    Äįan
    0.08
     ë°Ķë¡ľ
    0.08
    Activations Density 0.130%

    No Known Activations