© 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. 4704
    Prev
    Next
    INDEX
    Explanations

    specific words and punctuation

    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
    ׼×Ķ
    -0.08
    кÑĢов
    -0.07
    صÙĦ
    -0.07
    ׼×ķ
    -0.07
    ì´¬
    -0.07
    /background
    -0.06
    gang
    -0.06
    æ¸Ĭ
    -0.06
    ë°°
    -0.06
    zcze
    -0.06
    POSITIVE LOGITS
    宿
    0.08
    ä¸Ģå¤ķ
    0.08
    ATIV
    0.07
    achim
    0.07
     Beno
    0.07
    ?!
    0.07
    æĺķ
    0.06
    unis
    0.06
    ByUrl
    0.06
    oureux
    0.06
    Activations Density 0.077%

    No Known Activations