© 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. 48129
    Prev
    Next
    INDEX
    Explanations

    vs, versus

    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
    大èĩªçĦ¶çļĦ
    -0.06
    bac
    -0.06
    bai
    -0.06
    asm
    -0.06
    ·
    -0.06
    æľīä¸Ģå®ļçļĦ
    -0.06
    spartner
    -0.06
    vet
    -0.05
    æ´»
    -0.05
    ä¹ĭæ³ķ
    -0.05
    POSITIVE LOGITS
     vs
    0.12
     versus
    0.09
     illustrate
    0.09
    _vs
    0.09
    å°±çŁ¥éģĵäºĨ
    0.09
    æĥħåĨµçŃī
    0.09
     ìĺĪ를
    0.09
    çļĦä¾ĭåŃIJ
    0.09
    çĤ¹åĩ»æŁ¥çľĭ
    0.09
    为ä¾ĭ
    0.09
    Activations Density 0.028%

    No Known Activations