© 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. 12576
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    èĭ¹
    -0.09
    oskop
    -0.07
    èĺĭ
    -0.07
    leks
    -0.06
    åĴĮ讯
    -0.06
    åī¯æł¡éķ¿
    -0.06
    our
    -0.06
    æĪijçļĦ家乡
    -0.06
    åĿİ
    -0.06
    ajt
    -0.06
    POSITIVE LOGITS
    ams
    0.08
    IfExists
    0.07
    ukes
    0.07
    orma
    0.07
    å°ĨæѤ
    0.07
    ÙĦÙĥ
    0.07
     DRIVE
    0.07
     benne
    0.07
    _BUCKET
    0.06
    ãĥķãĤ£
    0.06
    Activations Density 0.194%

    No Known Activations