© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 40514
    Prev
    Next
    INDEX
    Explanations

    variable assignment `=`

    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
    =='
    -0.08
    ==-
    -0.07
    =="
    -0.07
    =true
    -0.07
    !="
    -0.07
    :false
    -0.07
    arder
    -0.07
    vides
    -0.07
    ()==
    -0.07
    deos
    -0.07
    POSITIVE LOGITS
     =
    0.09
    ascript
    0.07
     <-
    0.07
    ä»ĸ竣çĦ¶
    0.07
     âĨIJ
    0.07
    åħ°çī¹
    0.07
    .setdefault
    0.07
     myself
    0.07
    ilik
    0.06
    æĢİä¹ĪåĬŀåij¢
    0.06
    Activations Density 0.057%

    No Known Activations