© 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. 16668
    Prev
    Next
    INDEX
    Explanations

    and or with

    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
    Negative Logits
    åıªèĥ½è¯´
    -0.05
    åı«
    -0.05
     enten
    -0.05
    ieux
    -0.05
    istik
    -0.05
    óm
    -0.05
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    -0.05
    either
    -0.05
    ì¹Ń
    -0.05
     either
    -0.04
    POSITIVE LOGITS
    ocen
    0.06
    erima
    0.06
    éĻ¤æѤä¹ĭå¤ĸ
    0.06
    erde
    0.06
    è¿Ļä¸Ģ
    0.06
     пÑĢоÑĩ
    0.06
    èĪ¬çļĦ
    0.06
    ä¹ĭå¤ĸçļĦ
    0.06
     esimer
    0.06
    _like
    0.06
    Activations Density 0.094%

    No Known Activations