© 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. 31298
    Prev
    Next
    INDEX
    Explanations

    image entries

    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
    åĨħå¿ĥä¸ĸçķĮ
    -0.07
    æ°ijé£İ
    -0.07
    æīĢåģļ
    -0.07
    身åIJİçļĦ
    -0.06
    åĬ¨è¾Ħ
    -0.06
    ration
    -0.06
    æĭ§
    -0.06
    ä¸ļåĬ¡ç´łè´¨
    -0.06
    éĽĦé¹°
    -0.06
     Forgotten
    -0.06
    POSITIVE LOGITS
    uchu
    0.09
    illot
    0.08
    åĵĪåĵĪåĵĪåĵĪ
    0.07
    ész
    0.07
     warta
    0.07
     cerebr
    0.07
    åĵĪåĵĪ
    0.07
     jahr
    0.07
    abez
    0.07
    伯æģ©
    0.07
    Activations Density 0.042%

    No Known Activations