© 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. 22343
    Prev
    Next
    INDEX
    Explanations

    replaced by

    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
    ykl
    -0.06
     عÙĦ
    -0.06
    æĪijåĴĮä½ł
    -0.06
    دÙħ
    -0.05
    ä»»ä½ķ人
    -0.05
    าย
    -0.05
    ---</
    -0.05
    ...*
    -0.05
    ercial
    -0.05
     :</
    -0.05
    POSITIVE LOGITS
     progression
    0.06
     imme
    0.06
    Derived
    0.05
    æīĭçļĦ
    0.05
    ấn
    0.05
    rior
    0.05
    为èį£
    0.05
    ×Ļת
    0.05
    ä¿©
    0.05
    enang
    0.05
    Activations Density 0.005%

    No Known Activations