© 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. 19185
    Prev
    Next
    INDEX
    Explanations

    bib, ref, subject, copyright, cms

    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
    osos
    -0.06
     Iphone
    -0.06
    bach
    -0.06
    à¥į
    -0.05
     Playstation
    -0.05
    osso
    -0.05
    æłĩçīĮ
    -0.05
     bergen
    -0.05
    æľ¬å¸ĸ
    -0.05
    å°ijéĥ¨åĪĨ
    -0.05
    POSITIVE LOGITS
     dies
    0.07
    ç«Ļ
    0.06
    omme
    0.05
    alm
    0.05
    iram
    0.05
    ias
    0.05
    íı¬
    0.05
    intes
    0.05
     Dies
    0.05
    æĮģ
    0.05
    Activations Density 0.001%

    No Known Activations