© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    radical chemistry

    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
    æ±Ĥç²¾
    -0.07
    åĩºè´§éĩı
    -0.07
    ãĤ¹ãĥ¡
    -0.07
     suon
    -0.07
     Trem
    -0.07
    Ñĭв
    -0.07
    éĴ£
    -0.07
    åĨįä¸Ĭæĸ°åı°éĺ¶
    -0.06
    ucked
    -0.06
     Silber
    -0.06
    POSITIVE LOGITS
    ä¸įçģŃ
    0.08
     initiated
    0.08
     initiation
    0.08
    -init
    0.08
    æŃ¤èµ·
    0.07
    cox
    0.07
     initiating
    0.07
     Init
    0.07
    -mediated
    0.07
    /photo
    0.07
    Activations Density 0.012%

    No Known Activations