© 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. 19552
    Prev
    Next
    INDEX
    Explanations

    functional group/ization

    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
    ä¼Ĺ
    -0.07
    çľ¾
    -0.05
    1
    -0.05
    ú
    -0.05
    硬
    -0.05
    ind
    -0.05
    ous
    -0.05
    å½¢çļĦ
    -0.05
    جز
    -0.05
    è¡Ĩ
    -0.05
    POSITIVE LOGITS
    kent
    0.07
    kla
    0.07
     reel
    0.06
    ompat
    0.06
    rof
    0.06
    eita
    0.06
    è¿ĩçļĦ
    0.06
    kala
    0.06
    istra
    0.06
    kia
    0.06
    Activations Density 0.016%

    No Known Activations