© 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. 62445
    Prev
    Next
    INDEX
    Explanations

    visualizations and graphs

    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
    á»±u
    -0.08
    kus
    -0.07
    åı
    -0.07
    æ¤į
    -0.07
    稿件æĿ¥æºIJ
    -0.07
    èĪĮå°ĸ
    -0.07
     antiqu
    -0.07
    彬彬
    -0.07
     explosive
    -0.07
    éĢŁ
    -0.07
    POSITIVE LOGITS
     depicting
    0.14
     visual
    0.14
     visualization
    0.14
    缴è§Ĥ
    0.14
     visualize
    0.13
    visualization
    0.13
    缴è§ĤçļĦ
    0.13
     graphical
    0.12
     visually
    0.12
    çĶ»æ³ķ
    0.12
    Activations Density 0.127%

    No Known Activations