© 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. 22424
    Prev
    Next
    INDEX
    Explanations

    numbers and references

    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
    cola
    -0.06
    оÑĢа
    -0.06
    ugo
    -0.06
    çºł
    -0.06
    èĽĢ
    -0.06
    acos
    -0.06
    zków
    -0.06
    threads
    -0.05
    printer
    -0.05
    qc
    -0.05
    POSITIVE LOGITS
    nitz
    0.05
     demand
    0.05
    æ´ģ
    0.05
    indo
    0.05
    orong
    0.05
    ulant
    0.05
    éĢŀ
    0.05
     hung
    0.05
    æĹ¥æĸ°æľĪ
    0.05
     hang
    0.05
    Activations Density 0.065%

    No Known Activations