© 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. 13182
    Prev
    Next
    INDEX
    Explanations

    growth and decay

    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
    umentos
    -0.09
    ceptors
    -0.09
    大èĥĨçļĦ
    -0.09
    inhos
    -0.08
    åĢĻ
    -0.08
    ztat
    -0.08
    è½°è½°
    -0.08
    åijµåijµ
    -0.08
    หา
    -0.08
    errupt
    -0.07
    POSITIVE LOGITS
     exponentially
    0.07
    å¿ĺäºĨ
    0.07
    tru
    0.07
    æľĢå¿«çļĦ
    0.07
    èĩ³
    0.07
    æĸ¹å¼ıæĺ¯
    0.07
    éĿĴæĿ¾
    0.07
    å¾Īå¿«
    0.06
    शà¥Ģ
    0.06
    æľŁçļĦ
    0.06
    Activations Density 0.005%

    No Known Activations