© 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. 16836
    Prev
    Next
    INDEX
    Explanations

    print output or calculated values

    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
    il
    -0.06
     laz
    -0.05
    æĹºçĽĽ
    -0.05
     temp
    -0.05
     transform
    -0.05
     grown
    -0.04
    oll
    -0.04
    ulam
    -0.04
     transformed
    -0.04
    èĮ¬
    -0.04
    POSITIVE LOGITS
    abar
    0.07
    å±Ģéķ·
    0.07
    lés
    0.07
    edan
    0.07
    Ïģια
    0.07
    rias
    0.07
    ancen
    0.06
    ä¹İåħ¶
    0.06
    æĹ¥åIJİçļĦ
    0.06
    hada
    0.06
    Activations Density 0.003%

    No Known Activations