© 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. 44958
    Prev
    Next
    INDEX
    Explanations

    states of being or comparison

    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
    ãĢįï¼Ī
    -0.08
    ï¼Ī
    -0.07
    åľ¨æŁIJäºĽ
    -0.07
    *,
    -0.07
    åºĶå½ĵä¾Ŀçħ§
    -0.06
    æij©
    -0.06
    **—
    -0.06
     (?
    -0.06
    —that
    -0.06
    *
    -0.06
    POSITIVE LOGITS
    ++.
    0.08
    kland
    0.08
    ./.
    0.08
    ï½ŀãĢĤ
    0.08
     ayrıca
    0.08
    æ´ŀéĩĮ
    0.08
    )}.
    0.07
    ì²
    0.07
     daÃŃ
    0.07
     rica
    0.07
    Activations Density 0.006%

    No Known Activations