© 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. 7177
    Prev
    Next
    INDEX
    Explanations

    hydrogen bonding

    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
    еÑģÑĤо
    -0.08
    Assembler
    -0.08
    lingen
    -0.08
    ãģ©ãĤĬ
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    aday
    -0.07
    åĬłçĽĸ
    -0.07
    apos
    -0.07
    æĮĩå®ļåľ°çĤ¹
    -0.07
    áy
    -0.07
    POSITIVE LOGITS
    ç¦ģ
    0.08
    -enabled
    0.07
     donors
    0.06
     رÙĪابط
    0.06
    ortable
    0.06
    -tooltip
    0.06
    é¢ľ
    0.06
    imba
    0.06
     donor
    0.06
    uds
    0.06
    Activations Density 0.003%

    No Known Activations