© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20663
    Prev
    Next
    INDEX
    Explanations

    charged with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umber
    -0.06
    clus
    -0.06
    imba
    -0.06
    vd
    -0.06
    ange
    -0.06
     Yorker
    -0.06
     available
    -0.05
    æľªè¢«
    -0.05
    quist
    -0.05
     trib
    -0.05
    POSITIVE LOGITS
    wall
    0.06
    æIJº
    0.06
     herself
    0.05
    æĮĩçĤ¹
    0.05
    家åºŃåĴĮ
    0.05
    лиÑĨа
    0.05
    apl
    0.05
    ä¸İ该
    0.05
    holders
    0.05
    ered
    0.05
    Activations Density 0.027%

    No Known Activations