© 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. 58078
    Prev
    Next
    INDEX
    Explanations

    questions about whether/how/concerns

    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
    assen
    -0.08
    resents
    -0.08
    åľ¨ä¸ĭè½½
    -0.07
    jih
    -0.07
    iams
    -0.07
    æ£ĴäºĨ
    -0.07
    клада
    -0.07
    ä¸ĢäºĽäºº
    -0.07
    æĽ´æĸ°æĹ¥æľŁ
    -0.07
    è¯ķè¯ķåIJ§
    -0.07
    POSITIVE LOGITS
    _EXEC
    0.07
    lrt
    0.07
    æ½Ł
    0.06
     executions
    0.06
    iko
    0.06
    æĤ¨çļĦ
    0.06
    mig
    0.06
    æ´
    0.06
    tl
    0.06
    å°
    0.06
    Activations Density 0.004%

    No Known Activations