© 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. 16554
    Prev
    Next
    INDEX
    Explanations

    registry source gems

    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
    ynos
    -0.06
    ç»ĵ
    -0.05
     ÐijÑĥд
    -0.05
    kept
    -0.05
    Ø¢Ùħد
    -0.05
     Pasti
    -0.05
    nants
    -0.05
    éª
    -0.05
     пÑĢовод
    -0.05
    ains
    -0.05
    POSITIVE LOGITS
    éĺŁåľ¨
    0.06
    éķľå¤´éĩĮ
    0.06
    åĪ«äºº
    0.06
    tua
    0.06
    baz
    0.06
     souten
    0.06
    (mu
    0.06
    oyer
    0.06
    ESCO
    0.05
    ç£ķ
    0.05
    Activations Density 0.022%

    No Known Activations