© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    value, age, commercial, package, order

    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
    omor
    -0.08
    icode
    -0.08
    è¡Ĺåı£
    -0.08
    大ä½ĵ
    -0.08
    ä¹ĭ以
    -0.08
    åĭī强
    -0.07
    ãģĤãģ¨ãģ¯
    -0.07
    .blog
    -0.07
    oom
    -0.07
    emale
    -0.07
    POSITIVE LOGITS
     Gru
    0.08
    çħ§æł·
    0.07
    omb
    0.07
    没éĹ®é¢ĺ
    0.07
    emy
    0.07
    没æľīéĹ®é¢ĺ
    0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    0.07
     etc
    0.06
    æĤīå¿ĥ
    0.06
    ä¸įä¹ı
    0.06
    Activations Density 0.059%

    No Known Activations