© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming concepts

    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
    央
    -0.06
    haut
    -0.06
    èĤ¯å®ļè¦ģ
    -0.06
    kia
    -0.06
    ода
    -0.05
    case
    -0.05
    IX
    -0.05
    æľŁ
    -0.05
    uari
    -0.05
    ä¸Ģå¤ķ
    -0.05
    POSITIVE LOGITS
     ngoÃłi
    0.06
     izg
    0.06
    ä¸įè§ģ
    0.06
    립
    0.05
    辦
    0.05
    bili
    0.05
    大楼
    0.05
    ffi
    0.05
    igna
    0.05
     retire
    0.05
    Activations Density 0.011%

    No Known Activations