© 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. 20041
    Prev
    Next
    INDEX
    Explanations

    separations, FileManager, ascending, Payments, over

    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
    en
    -0.06
    -0.05
    æıIJåĩº
    -0.05
    æ¹
    -0.05
    or
    -0.05
    avi
    -0.05
    æľī人
    -0.05
    adapt
    -0.05
    -
    -0.05
    ãģĵãģ¨ãģĮãģ§ãģįãĤĭ
    -0.05
    POSITIVE LOGITS
    вÑĢ
    0.07
    ấy
    0.06
    راÛĮÙĨ
    0.06
    .§
    0.06
    ại
    0.06
    åĪ°æѤ
    0.06
    hlas
    0.06
    VáºŃy
    0.06
    -final
    0.06
    সà§įত
    0.06
    Activations Density 0.001%

    No Known Activations