© 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. 59057
    Prev
    Next
    INDEX
    Explanations

    find anyone who is

    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
    éĩijçŁ³
    -0.08
    åĶ¯ä¸Ģ
    -0.07
    æıĴ
    -0.07
    ube
    -0.07
    èĸ°
    -0.07
    ÙĪÙĨØ©
    -0.06
    æłij人
    -0.06
    ç³ľ
    -0.06
    è´º
    -0.06
    èĥ
    -0.06
    POSITIVE LOGITS
    åħĪçľĭ
    0.10
    åħĪ
    0.10
    åħĪåľ¨
    0.09
    é¦ĸåħĪæĺ¯
    0.08
    åħĪæĿ¥
    0.08
    æĺ¯åħĪ
    0.08
    åħĪå°Ĩ
    0.08
    æīĵ人
    0.08
    åħĪåĪ°
    0.08
    ä½łåħĪ
    0.08
    Activations Density 0.001%

    No Known Activations