© 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. 18805
    Prev
    Next
    INDEX
    Explanations

    dimensions and sizes

    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
    ÑģиÑħо
    -0.06
    oblins
    -0.06
    okus
    -0.06
    ÙĪÙĬات
    -0.06
    avais
    -0.06
    à¹Ĥà¸ĭà¸Ļ
    -0.06
    VISIBLE
    -0.06
    åħĮ
    -0.06
    家åĸ»
    -0.06
    Ú¯ÙĪÙĨ
    -0.06
    POSITIVE LOGITS
    ier
    0.06
    o
    0.06
    ic
    0.05
    ä¸įæĶ¶
    0.05
     opposite
    0.05
    ed
    0.05
    à¹Į
    0.05
    e
    0.05
    æŀĦ
    0.05
     tally
    0.05
    Activations Density 0.001%

    No Known Activations