© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16873
    Prev
    Next
    INDEX
    Explanations

    companies, acronyms, and specific technical terms

    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
    ziÄĻki
    -0.06
    lec
    -0.06
    anter
    -0.06
    å·²ç»ıæľīäºĨ
    -0.06
    åĮĸåѦ
    -0.05
    æ¯ĶæĻ®éĢļ
    -0.05
    rik
    -0.05
     ellen
    -0.05
    lijk
    -0.05
    оÑĢÑĤ
    -0.05
    POSITIVE LOGITS
    icana
    0.06
    erait
    0.06
    orada
    0.05
    tez
    0.05
    jon
    0.05
    ุม
    0.05
    owell
    0.05
    ãĤĤãģĹãĤį
    0.05
    äºĭ件ä¸Ń
    0.05
    verd
    0.05
    Activations Density 0.001%

    No Known Activations