© 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. 51970
    Prev
    Next
    INDEX
    Explanations

    lost, lonely, bleak, or homeless

    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
     feu
    -0.07
    æĸĩåįļ
    -0.07
    æĪIJé¾Ļ
    -0.06
    ipro
    -0.06
    æİĴæ¯Ĵ
    -0.06
    दार
    -0.06
     mừng
    -0.06
    éĺ²æļij
    -0.06
    ä¹ĭæģ©
    -0.06
     climat
    -0.06
    POSITIVE LOGITS
    æĹłåĬ©
    0.12
    æĹłéĻħ
    0.10
     lonely
    0.10
    à¹Ħรà¹ī
    0.10
    å¢ĥåľ°
    0.10
    彷徨
    0.09
    åѤå¯Ĥ
    0.09
    åѤ
    0.09
    æĹłå°½çļĦ
    0.09
    åѤçĭ¬
    0.09
    Activations Density 0.089%

    No Known Activations