© 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. 59916
    Prev
    Next
    INDEX
    Explanations

    layer or layering

    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
    ÑĥÑĢо
    -0.08
    esser
    -0.08
    ether
    -0.08
    临éŨ
    -0.08
    ä¸įèĩªç¦ģ
    -0.08
    ÅĤyn
    -0.07
    anders
    -0.07
    åĮ»ç§ij大åѦ
    -0.07
    avu
    -0.07
    หมาย
    -0.07
    POSITIVE LOGITS
    èĸĦèĸĦçļĦ
    0.10
    ing
    0.10
    tere
    0.09
    wise
    0.09
     belakang
    0.09
    edin
    0.08
    arity
    0.08
    à¸ģวà¹Īา
    0.08
    ÑĩаÑĤ
    0.08
    éĿ¢ä¸ĬçļĦ
    0.08
    Activations Density 0.026%

    No Known Activations