© 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. 7178
    Prev
    Next
    INDEX
    Explanations

    "scale" : "3x"

    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
     <+
    -0.06
    .tpl
    -0.06
    rs
    -0.06
    heim
    -0.06
    çĦ¶å¤§
    -0.06
    æľĪ份å¼Ģå§ĭ
    -0.06
    essen
    -0.06
    为主导
    -0.06
    ora
    -0.06
    æĪ·æĻĵ
    -0.06
    POSITIVE LOGITS
    antro
    0.09
    andro
    0.08
    ä¸įæĶ¶
    0.08
    asten
    0.08
    ANH
    0.07
    uchy
    0.07
    ä¸įåı¯ä»¥
    0.07
    erb
    0.07
    èĪ¶
    0.07
    äst
    0.07
    Activations Density 0.014%

    No Known Activations