© 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. 54941
    Prev
    Next
    INDEX
    Explanations

    examplefollowed by comma or specific English words

    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
    loff
    -0.08
    åıĪåĥı
    -0.07
    umer
    -0.07
    .asc
    -0.07
     Faul
    -0.07
    å¤ļè¿ľ
    -0.07
    TextNode
    -0.07
    ложением
    -0.07
    emen
    -0.07
    tual
    -0.07
    POSITIVE LOGITS
     example
    0.07
    bol
    0.07
    åıijæ¶Īæģ¯
    0.07
     exemple
    0.07
    éĩijçłĸ
    0.06
    -example
    0.06
    ijs
    0.06
    example
    0.06
    æľ¬åľºæ¯ĶèµĽ
    0.06
    åijµåijµ
    0.06
    Activations Density 0.001%

    No Known Activations