© 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. 16610
    Prev
    Next
    INDEX
    Explanations

    number followed by units or descriptive terms

    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
    гÑĢада
    -0.06
     поÑģл
    -0.06
     '{}'
    -0.06
    ÙĦاØŃ
    -0.06
    ãģ¿
    -0.06
     adel
    -0.06
    اÙĨØ´
    -0.06
    icule
    -0.06
    å¼ķéĩı
    -0.05
     mieux
    -0.05
    POSITIVE LOGITS
    -a
    0.05
    -it
    0.05
    ä¸Ģç»ı
    0.05
    æįŁçĽĬ
    0.05
    çĹ´
    0.05
    âĢ¦
    0.05
    -L
    0.04
    ör
    0.04
     intu
    0.04
    azing
    0.04
    Activations Density 0.051%

    No Known Activations