© 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. 16705
    Prev
    Next
    INDEX
    Explanations

    dioxin, rotating, duct tape, oncology, increasing, two, survey, long

    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
    å¾ĢæľŁç²¾å½©
    -0.06
    çŁ¥
    -0.06
    äºĶèĬ±
    -0.06
    past
    -0.06
    æĥ³
    -0.06
    entas
    -0.06
    åĪ°é«ĺ
    -0.06
     oppf
    -0.05
    å¦Ĥæŀľä½łæĥ³
    -0.05
    ç§ģ
    -0.05
    POSITIVE LOGITS
    æŀ¢
    0.06
     lu
    0.06
    ãĤ¯ãĥ«
    0.05
    èĦĬ
    0.05
    -plus
    0.05
    adá
    0.05
    æ¡ĵ
    0.05
    seb
    0.05
    ereo
    0.05
    uno
    0.05
    Activations Density 0.273%

    No Known Activations