© 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. 19348
    Prev
    Next
    INDEX
    Explanations

    media from, data, player, company, manipulation

    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
    shaw
    -0.07
    shire
    -0.07
    kest
    -0.06
    yle
    -0.06
    atology
    -0.06
    shan
    -0.06
    æ¯Ķäºļ
    -0.06
    wurf
    -0.06
    iling
    -0.06
    icle
    -0.06
    POSITIVE LOGITS
    hips
    0.07
    acente
    0.06
    à¹Į
    0.06
    ìĦ¯
    0.06
    fore
    0.06
    plice
    0.06
    uca
    0.06
    ungkap
    0.06
    haps
    0.06
    VERSE
    0.06
    Activations Density 0.027%

    No Known Activations