© 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. 52101
    Prev
    Next
    INDEX
    Explanations

    prime numbers and sequences

    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
    åIJĬ
    -0.06
    ar
    -0.06
    us
    -0.06
    ä¸įèµ·æĿ¥
    -0.06
    unci
    -0.06
     bias
    -0.06
    åĬĽåĽ¾
    -0.06
     interpret
    -0.06
    饶
    -0.06
    æľīçļĦæŶåĢĻ
    -0.06
    POSITIVE LOGITS
    adém
    0.08
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    illers
    0.08
    postav
    0.08
     Chinh
    0.07
    çIJ³å¨ľ
    0.07
    yto
    0.07
    posti
    0.07
    -plugins
    0.07
    .aws
    0.07
    Activations Density 0.003%

    No Known Activations