© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20780
    Prev
    Next
    INDEX
    Explanations

    HTML, Star, limit, convex

    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
    гелÑĮ
    -0.09
    ¢
    -0.08
    çĶŁç´ł
    -0.08
    γο
    -0.08
    менÑĤ
    -0.08
    ikip
    -0.08
    etz
    -0.07
    ³
    -0.07
    segue
    -0.07
     $_
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.06
     czyli
    0.06
    abel
    0.06
    avis
    0.06
    oto
    0.06
    é£İå°ĺ
    0.06
    an
    0.06
     abbreviation
    0.06
     latter
    0.06
    orts
    0.06
    Activations Density 0.128%

    No Known Activations