© 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. 22482
    Prev
    Next
    INDEX
    Explanations

    porphyrin, p-nitro, zidovudine, dp, Roman jurist

    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
    mares
    -0.06
    koch
    -0.06
    é¤IJé»ŀ
    -0.06
    åıĬ个人
    -0.06
    aranja
    -0.06
    ä¸Ń级
    -0.06
    avance
    -0.06
    寮
    -0.06
    ["$
    -0.06
     .**
    -0.06
    POSITIVE LOGITS
     trá»įng
    0.05
    iste
    0.05
     Wunder
    0.05
    ä»»
    0.05
    oot
    0.05
    æłĩ
    0.05
    istinguished
    0.05
    ierto
    0.05
    uste
    0.05
    éļıé£İ
    0.05
    Activations Density 0.009%

    No Known Activations