© 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. 16781
    Prev
    Next
    INDEX
    Explanations

    boxes or items

    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
     transform
    -0.05
     transition
    -0.05
    transform
    -0.05
     widely
    -0.05
    ä¸įæİ¥åıĹ
    -0.05
     transformed
    -0.05
     transitions
    -0.05
     Personal
    -0.05
     t
    -0.05
    -0.05
    POSITIVE LOGITS
    èĬĤ
    0.07
     atrac
    0.06
    existent
    0.06
    etek
    0.06
    lá
    0.06
     urgent
    0.06
    ismi
    0.06
    identi
    0.06
    ÅĤów
    0.06
    çªģçł´åı£
    0.06
    Activations Density 0.003%

    No Known Activations