© 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. 22050
    Prev
    Next
    INDEX
    Explanations

    matrix mathematics

    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
    è¿ĻæĿ¡
    -0.07
    å²Ķ
    -0.07
     hal
    -0.06
     Belmont
    -0.06
     Dust
    -0.06
    æĤłæĤł
    -0.06
     redraw
    -0.06
     Red
    -0.06
    çݯ线
    -0.06
    串èģĶ
    -0.06
    POSITIVE LOGITS
    tensor
    0.09
    erator
    0.09
     matrices
    0.09
     маÑĤÑĢи
    0.08
    matrix
    0.08
    磩éĺµ
    0.08
     NotImplemented
    0.08
     tensor
    0.08
    åĴĮå¼ł
    0.08
     Decompiled
    0.08
    Activations Density 0.014%

    No Known Activations