© 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. 16662
    Prev
    Next
    INDEX
    Explanations

    map or assign

    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
    åŃĺåľ¨äºİ
    -0.08
    åİħéķ¿
    -0.07
     Pue
    -0.07
    azon
    -0.06
    æĹ¥çħ§
    -0.06
    ä¹ĭæķ°
    -0.06
    çļĦåŃĺåľ¨
    -0.06
    飬
    -0.06
    åŃĺåľ¨
    -0.06
     tipped
    -0.06
    POSITIVE LOGITS
    animate
    0.08
     mapping
    0.08
    assign
    0.08
    adak
    0.08
    OMP
    0.08
    åIJĮæŶå°Ĩ
    0.07
    Õ¸Õ¾
    0.07
    é¢Ĩ导åıĬ
    0.07
    mapping
    0.07
    iston
    0.07
    Activations Density 0.006%

    No Known Activations