© 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. 52035
    Prev
    Next
    INDEX
    Explanations

    used for example

    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
     ero
    -0.08
    ero
    -0.08
    alm
    -0.07
    åĢĴåľ¨
    -0.07
    ako
    -0.07
    æ²½
    -0.07
    oule
    -0.07
    æºī
    -0.07
    ERO
    -0.07
    -su
    -0.07
    POSITIVE LOGITS
    该éĻ¢
    0.07
    éķ¿å¤Ħ
    0.07
    æī¬åŃIJ
    0.07
    è¿ĽæĿij
    0.07
    éĤ£åĦ¿
    0.07
    åĻĮ
    0.06
    鸳
    0.06
     Verka
    0.06
     Credential
    0.06
    apesh
    0.06
    Activations Density 0.331%

    No Known Activations