© 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. 55912
    Prev
    Next
    INDEX
    Explanations

    ignore or exclude

    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
    à¦ĺ
    -0.08
    umba
    -0.08
    æĹłè¯¯
    -0.07
     GLint
    -0.07
    åıªèĥ½è¯´
    -0.06
    ystal
    -0.06
    ãģĹãģĭãĤĤ
    -0.06
    uwen
    -0.06
    ä¸ĿçļĦ
    -0.06
    åĽ½å¼º
    -0.06
    POSITIVE LOGITS
    ä¸įäºĪ
    0.11
    ä¸į计
    0.11
    ä¸įåıĤä¸İ
    0.10
    agno
    0.09
     exclude
    0.09
     excluded
    0.09
     altogether
    0.09
     khá»ıi
    0.08
    ignored
    0.08
    Exclude
    0.08
    Activations Density 0.049%

    No Known Activations