© 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. 22313
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    apres
    -0.06
    tabla
    -0.06
    atici
    -0.06
    alay
    -0.06
    actualité
    -0.06
    à¸Ķัà¸ĩ
    -0.06
    иа
    -0.06
    Ñģи
    -0.05
    éĢ£
    -0.05
    ữa
    -0.05
    POSITIVE LOGITS
     tand
    0.05
     appro
    0.05
    ose
    0.05
    缸åºĶ
    0.05
    à¥ĩल
    0.05
     progress
    0.05
    éĩĮ头
    0.05
     Cun
    0.05
     âĢ¦
    0.05
    ãĥªãĥ³
    0.05
    Activations Density 0.702%

    No Known Activations