© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21652
    Prev
    Next
    INDEX
    Explanations

    use in, waves offers, pieces unite, system contributes

    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
    ç»´æĸ¯
    -0.06
    pas
    -0.06
     vik
    -0.06
    DAH
    -0.06
    sud
    -0.05
    严éĩįç¨ĭ度
    -0.05
    对åħ¶è¿Ľè¡Į
    -0.05
    ç¼ł
    -0.05
    evel
    -0.05
    entas
    -0.05
    POSITIVE LOGITS
    ×ķ×ļ
    0.06
     ÙħÙĪرد
    0.06
    ä¸įæŃ»
    0.05
    aken
    0.05
    .Hour
    0.05
    iett
    0.05
    人éĢł
    0.05
    ×¢×Ļ
    0.05
    .Core
    0.05
     metal
    0.05
    Activations Density 0.015%

    No Known Activations