© 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. 65021
    Prev
    Next
    INDEX
    Explanations

    pretence and disguise

    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
    avia
    -0.08
    .definition
    -0.08
    ogle
    -0.08
    åĩĮ空
    -0.08
    StatusCode
    -0.08
    å·´æİĮ
    -0.08
    åĪ©çī©
    -0.07
    צ׾
    -0.07
    inker
    -0.07
    fen
    -0.07
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.14
     бÑĥдÑĤо
    0.10
     pretend
    0.09
     supposedly
    0.09
    è£ħä½ľ
    0.09
     ostensibly
    0.09
     fict
    0.09
     faux
    0.09
     fake
    0.08
     seolah
    0.08
    Activations Density 0.190%

    No Known Activations