© 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. 33629
    Prev
    Next
    INDEX
    Explanations

    gut feelings and intuition

    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
     specta
    -0.08
    ä¸įåłª
    -0.08
    æĢĴçģ«
    -0.07
    akedown
    -0.07
    çļĦé«ĺå³°
    -0.07
    ä¸įæĸĻ
    -0.07
    .flat
    -0.07
     зÑĥбÑĭ
    -0.07
    åıįéĿ¢
    -0.07
    /MIT
    -0.07
    POSITIVE LOGITS
    缴è§ī
    0.14
    èİ«åIJįçļĦ
    0.14
     intuit
    0.13
    èİ«åIJį
    0.12
    æĦŁè§ī
    0.11
    ä¸į对åĬ²
    0.11
     feels
    0.11
    æĢ»æĦŁè§ī
    0.11
     felt
    0.11
     feel
    0.11
    Activations Density 0.327%

    No Known Activations