© 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. 17994
    Prev
    Next
    INDEX
    Explanations

    friends, family, or groups

    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
     некоÑĤоÑĢ
    -0.06
    åľº
    -0.06
    æī§è¡Į
    -0.06
    ắng
    -0.06
    sak
    -0.05
     giro
    -0.05
    indung
    -0.05
    æĬĺ
    -0.05
    cano
    -0.05
    ç§į
    -0.05
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.07
    пÑı
    0.06
    ä¹Łæĺ¯è¿Ļæł·
    0.05
    awah
    0.05
    ubic
    0.05
    ukas
    0.05
    ä¹Łä¸įä¾ĭå¤ĸ
    0.05
    åĪ·æĸ°
    0.05
    å°ı天
    0.05
    许å¤ļ人
    0.05
    Activations Density 0.114%

    No Known Activations