© 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. 4402
    Prev
    Next
    INDEX
    Explanations

    "Let", "suppose", "what", "which"

    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
    succ
    -0.08
    æĿ¥æºIJç½ij绾
    -0.07
    achts
    -0.07
    å§Ķ书记
    -0.07
    è¿Ļä¸ªåľ°æĸ¹
    -0.07
    ieurs
    -0.07
    å°±æĺ¯ä¸ºäºĨ
    -0.07
    elligen
    -0.07
    ernal
    -0.07
    尾页
    -0.07
    POSITIVE LOGITS
    åĬĽæĮº
    0.07
    cona
    0.06
    ç¾Į
    0.06
    veau
    0.06
    豪
    0.06
    Wo
    0.06
    enste
    0.06
    ä¿Ĥ
    0.06
    declar
    0.05
    æĪ®
    0.05
    Activations Density 0.060%

    No Known Activations