© 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. 16707
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    æĦŁæĢ§
    -0.07
    人çĶŁçļĦ
    -0.06
    ãģ°
    -0.06
    åı¯æľĽ
    -0.06
    elingen
    -0.06
    æľ¬æĬ¥åijĬ
    -0.06
    çļĦè¯Ħä»·æĺ¯
    -0.05
    æľĢä½³çļĦ
    -0.05
    ä¸įèĥ½çĶ¨
    -0.05
    mere
    -0.05
    POSITIVE LOGITS
    çİĭå¿Ĺ
    0.06
    mand
    0.06
    kle
    0.05
     пÑĢизнак
    0.05
     intentionally
    0.05
    æł¹æį®éľĢè¦ģ
    0.05
     purposely
    0.05
    æĭĽåij¼
    0.05
    ãĤĴçĻº
    0.05
    اء
    0.05
    Activations Density 0.017%

    No Known Activations