© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 1135
    Prev
    Next
    INDEX
    Explanations

    same, degree, similar, resembling

    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
    ingu
    -0.06
    é¢ľ
    -0.06
     permanently
    -0.06
     mistr
    -0.06
     guiding
    -0.06
    æĺĮåİ¿
    -0.06
     Sticky
    -0.06
    lott
    -0.06
    æĺ¯ä¸Ģéģĵ
    -0.06
     Permanent
    -0.06
    POSITIVE LOGITS
    ä¸İæĻ®éĢļ
    0.15
    类似äºİ
    0.14
     resembling
    0.14
     layaknya
    0.13
     resembles
    0.13
     resemble
    0.13
    à¹Ģหมืà¸Ńà¸Ļà¸ģัà¸ļ
    0.13
    ä¸İä¼łç»Ł
    0.13
    å¾Īåĥı
    0.13
    åĴĮæĻ®éĢļ
    0.13
    Activations Density 0.440%

    No Known Activations