© 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. 7540
    Prev
    Next
    INDEX
    Explanations

    smiling or smiled

    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
    ÑīеÑĤ
    -0.08
    æĢ§åľ°
    -0.08
    ´
    -0.08
    èĢ³çĽ®
    -0.08
    è´¨çļĦ
    -0.07
    afort
    -0.07
     didik
    -0.07
    ertext
    -0.07
    erras
    -0.07
    ä¸įåłª
    -0.06
    POSITIVE LOGITS
    ä¸Ģç¬ij
    0.09
    ingly
    0.08
     ÑĥлÑĭб
    0.08
    åĴĮçIJĨ解
    0.07
    å¾®ç¬ij
    0.07
     ÑĥлÑĭ
    0.07
    ÑĦÑĦ
    0.07
    èĬ±èIJ½
    0.07
    able
    0.07
    èĥĮåIJİ
    0.07
    Activations Density 0.025%

    No Known Activations