© 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. 647
    Prev
    Next
    INDEX
    Explanations

    special characters and suffixes

    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
    ation
    -0.12
    tır
    -0.09
    ़
    -0.09
    eur
    -0.09
    abay
    -0.08
    tures
    -0.08
    rrha
    -0.08
    ively
    -0.08
    大åĪ©
    -0.08
    ured
    -0.08
    POSITIVE LOGITS
    er
    0.16
    缸è¾ħ缸æĪIJ
    0.14
    æĸ°åĬłåĿ¡
    0.13
    åĬłæĭ¿å¤§
    0.12
    enticate
    0.12
    ities
    0.11
    áĢ¸
    0.11
    ÙĨ
    0.11
    å¤ļãģĦ
    0.11
    åĭĩå¾Ģ缴åīį
    0.11
    Activations Density 0.002%

    No Known Activations