© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19428
    Prev
    Next
    INDEX
    Explanations

    recipe instructions

    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
     trasc
    -0.07
    idad
    -0.06
    prac
    -0.05
    æĸ°çĶŁçļĦ
    -0.05
     Alone
    -0.05
    ä»İä¸ļ
    -0.05
    满
    -0.05
    ities
    -0.05
    嵩
    -0.05
    ul
    -0.05
    POSITIVE LOGITS
    rey
    0.06
     Ven
    0.05
    شت
    0.05
     ven
    0.05
     pee
    0.05
    注æĦıåĬĽ
    0.05
    å¯ĴåĨ°
    0.05
    çĻ½è¡Ģ
    0.05
    aul
    0.05
    Ven
    0.05
    Activations Density 0.005%

    No Known Activations