© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34971
    Prev
    Next
    INDEX
    Explanations

    lists of numbers

    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
    Negative Logits
    ä¸Ģè§ī
    -0.07
    /**/*.
    -0.07
    Animator
    -0.07
    åĩºçİ°éĹ®é¢ĺ
    -0.06
    讹
    -0.06
    念念ä¸įå¿ĺ
    -0.06
    verket
    -0.06
     renc
    -0.06
    Beg
    -0.06
    æĢ¥åĪĩ
    -0.06
    POSITIVE LOGITS
    åIJĦç§įåIJĦæł·
    0.07
    none
    0.07
    tty
    0.07
     None
    0.07
    į¼
    0.07
    éĵĤ
    0.07
    ilis
    0.07
    mute
    0.07
    象
    0.07
    ä½Ĩæĺ¯å®ĥ
    0.07
    Activations Density 0.012%

    No Known Activations