© 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. 54909
    Prev
    Next
    INDEX
    Explanations

    primality questions

    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
     lenght
    -0.09
    jni
    -0.09
    æĥħçļĦ
    -0.09
     Leban
    -0.09
    ulich
    -0.09
    length
    -0.08
    lean
    -0.08
    eben
    -0.08
    liner
    -0.08
    hle
    -0.08
    POSITIVE LOGITS
    éļĶ
    0.06
    åij¨è¾¹
    0.06
     squares
    0.06
    æ»ķ
    0.06
    รัส
    0.06
    nya
    0.06
    vog
    0.06
    æ¶Łæ¼ª
    0.05
    æ¦ķ
    0.05
    è¿Ļæĺ¯
    0.05
    Activations Density 0.021%

    No Known Activations