© 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. 50674
    Prev
    Next
    INDEX
    Explanations

    names of authors and philosophers

    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
    otas
    -0.09
    æ¥ļæ¥ļ
    -0.07
    rome
    -0.07
    igura
    -0.07
    abama
    -0.07
    åĪ°è¿Ļ
    -0.06
    BSD
    -0.06
    è°·éĽ¨
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    æĺ¯ä»ĸ们
    -0.06
    POSITIVE LOGITS
    大åIJį
    0.07
    isti
    0.07
    ledon
    0.07
    æĬĵèIJ½å®ŀ
    0.07
    åĪĻ认为
    0.07
    èIJ½å®ŀ好
    0.07
    天å¤ĸ
    0.06
    è¦ĸ
    0.06
    åħ¶èģĮ
    0.06
    emberg
    0.06
    Activations Density 0.079%

    No Known Activations