© 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. 18985
    Prev
    Next
    INDEX
    Explanations

    except followed by exclusion

    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
    åļ
    -0.07
     procéd
    -0.05
    aner
    -0.05
    leih
    -0.05
    人æīĢ
    -0.05
    æĪĪ
    -0.05
    æīį被
    -0.05
    onton
    -0.05
    اÙħ
    -0.05
    unid
    -0.05
    POSITIVE LOGITS
    ness
    0.09
    ä¸ļçļĦ
    0.07
    æķĻäºİ
    0.06
    messe
    0.06
    esz
    0.06
    rasz
    0.06
    eed
    0.06
    é½IJé½IJ
    0.06
    ÑĮо
    0.06
    æ¯ıä¸Ģ个人
    0.06
    Activations Density 0.015%

    No Known Activations