© 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. 34726
    Prev
    Next
    INDEX
    Explanations

    sector union

    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
    Not in Any Lists

    No Comments

    Negative Logits
    hey
    -0.07
    å¦ĤæĦı
    -0.07
    eway
    -0.06
    cut
    -0.06
    å®īçĦ¶
    -0.06
    alen
    -0.06
    orsz
    -0.06
    æİĮæı¡çļĦ
    -0.06
    ä¸Ģè¿ŀ
    -0.06
    Originally
    -0.06
    POSITIVE LOGITS
    èĨ½
    0.08
    åĪĨä¸Ńå¿ĥ
    0.08
    utc
    0.08
    á»Ńng
    0.08
    è¨Ģä¹ĭ
    0.08
    elok
    0.07
    .Names
    0.07
     ("<
    0.07
    ely
    0.07
    ç½Ħ
    0.07
    Activations Density 0.035%

    No Known Activations