© 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. 24772
    Prev
    Next
    INDEX
    Explanations

    their [possessive noun]

    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
    ié
    -0.08
    ìį¨
    -0.08
    ÙĬØ©
    -0.07
    à§į
    -0.07
    othy
    -0.07
    å¤ļæł·çļĦ
    -0.07
    ie
    -0.07
    agnol
    -0.07
    omics
    -0.07
    edis
    -0.07
    POSITIVE LOGITS
     own
    0.15
     respective
    0.12
    /her
    0.11
    sing
    0.10
    sed
    0.10
    editary
    0.09
     usual
    0.09
    ths
    0.09
     OWN
    0.09
    ÏĤ
    0.09
    Activations Density 0.547%

    No Known Activations