© 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. 22439
    Prev
    Next
    INDEX
    Explanations

    hunting

    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
    ס×Ķ
    -0.06
    å¥
    -0.06
    voj
    -0.06
    æĶ¾ä»»
    -0.06
    almaz
    -0.06
    åľ¨åįİ
    -0.05
    apé
    -0.05
    大好
    -0.05
    AFE
    -0.05
    å®°
    -0.05
    POSITIVE LOGITS
     sitten
    0.06
     "%"
    0.06
    ä¸įèĪį
    0.06
    unts
    0.05
    outers
    0.05
    że
    0.05
    ÙĪار
    0.05
    ockey
    0.05
     Ñīе
    0.05
    unting
    0.05
    Activations Density 0.053%

    No Known Activations