© 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. 16678
    Prev
    Next
    INDEX
    Explanations

    Berlin, disabilities, rain, wooded, orphan, cup

    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
    arry
    -0.06
    hing
    -0.06
     sel
    -0.06
    atem
    -0.05
    itors
    -0.05
    adapt
    -0.05
    åĴĮè°ĥæķ´
    -0.05
     eh
    -0.05
     pes
    -0.05
    åij½çļĦ
    -0.05
    POSITIVE LOGITS
     Weinstein
    0.06
    corp
    0.06
    æī¿åĬŀçļĦ
    0.05
    ouvre
    0.05
    ÑĩÑĮÑı
    0.05
    åľ¨åħĪ
    0.05
    èº«åľ¨
    0.05
    utta
    0.05
    åĪ©çĶ¨å¥½
    0.05
    Corp
    0.05
    Activations Density 0.144%

    No Known Activations