© 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. 14431
    Prev
    Next
    INDEX
    Explanations

    is a/are a

    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
    licit
    -0.07
    åĽ¾çŃī
    -0.07
    åħ¶å®ĥ
    -0.07
    è¯ĿæĿ¥
    -0.07
    ä»İèĢĮ
    -0.07
    aisseur
    -0.07
    æŃ£æĺ¯åĽłä¸º
    -0.06
    gebung
    -0.06
    iels
    -0.06
    æĹłä»¥
    -0.06
    POSITIVE LOGITS
    åħ³äºİè¿Ľä¸ĢæŃ¥
    0.09
    meth
    0.08
    çĽ¸å¯¹èĢĮè¨Ģ
    0.07
     berupa
    0.07
    ament
    0.07
     عبارة
    0.07
    ä¸Ģ个ç®ĢåįķçļĦ
    0.07
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.07
    ÙİÙĬÙĴ
    0.07
    elah
    0.07
    Activations Density 0.094%

    No Known Activations