© 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. 9457
    Prev
    Next
    INDEX
    Explanations

    user `id` `password` `body`

    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
    ographies
    -0.08
    жаÑħ
    -0.07
    éh
    -0.07
    innie
    -0.07
    æĸĩæijĺ
    -0.07
    affer
    -0.07
    å°±æĺ¯ä»¥
    -0.06
    åĨħ容åĮħæĭ¬
    -0.06
     khiá»ĥn
    -0.06
    avigate
    -0.06
    POSITIVE LOGITS
    accio
    0.09
    è¦ģä¹Ī
    0.08
    Included
    0.08
    either
    0.08
     either
    0.08
    included
    0.08
     Darling
    0.08
    æĹłåħ³
    0.07
    ä½ľä¸ºä¸Ģ个
    0.07
    åľ¨ä¸Ń
    0.07
    Activations Density 0.027%

    No Known Activations