© 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. 23852
    Prev
    Next
    INDEX
    Explanations

    derivatives and transformation of

    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
     ste
    -0.07
    足
    -0.06
    èıģ
    -0.06
    åĴĮé£İ
    -0.06
     concern
    -0.06
     Mojo
    -0.06
    hun
    -0.06
    åĮ¡
    -0.06
     Infer
    -0.06
    ynchron
    -0.06
    POSITIVE LOGITS
     thereof
    0.13
    çīĪçļĦ
    0.10
    äºĨçļĦ
    0.09
    εδ
    0.09
    å½¢å¼ıçļĦ
    0.08
    Ø«
    0.07
     daarvan
    0.07
    çīĪ
    0.07
    (torch
    0.07
    _of
    0.07
    Activations Density 0.259%

    No Known Activations