© 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. 20258
    Prev
    Next
    INDEX
    Explanations

    mathematical contexts

    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
    æİ°
    -0.08
    æķıæĦŁæĢ§
    -0.08
    æķ°çłģ
    -0.08
    æķıæĦŁåº¦
    -0.08
    arit
    -0.07
     ÙħجتÙħع
    -0.07
    ogra
    -0.07
    undert
    -0.07
    两æĢ§
    -0.06
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.06
    POSITIVE LOGITS
    raft
    0.07
    omid
    0.07
    orman
    0.07
    èĢģ乡
    0.07
    ensen
    0.07
    -lat
    0.06
     elementType
    0.06
    åĩºå¢ĥ
    0.06
    è°§
    0.06
    urent
    0.06
    Activations Density 0.001%

    No Known Activations