© 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. 26313
    Prev
    Next
    INDEX
    Explanations

    abstracts and code snippets

    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
    oret
    -0.08
    á»ĩn
    -0.07
    orit
    -0.07
    è´±
    -0.07
    æŦ
    -0.07
    æĢª
    -0.07
    erness
    -0.07
    son
    -0.07
    æĥ³èµ·æĿ¥
    -0.07
    èĴĻ
    -0.06
    POSITIVE LOGITS
    _named
    0.07
    à¸ļัà¸Ļ
    0.07
    _verbose
    0.07
    pron
    0.07
     Ged
    0.07
    èī¯
    0.07
    åŃ°
    0.07
    Typed
    0.07
    åIJĦçıŃ
    0.06
    éĩijçİī
    0.06
    Activations Density 0.001%

    No Known Activations