© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22166
    Prev
    Next
    INDEX
    Explanations

    medical and economic terms

    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
    alÄ±ÅŁ
    -0.06
    unge
    -0.06
    tester
    -0.06
    hão
    -0.06
     Gri
    -0.06
    ured
    -0.06
    ãĥĭãĥ³ãĤ°
    -0.06
    #ad
    -0.06
    æŃ£å¸¸çļĦ
    -0.06
    çļĦèĬ±
    -0.06
    POSITIVE LOGITS
    çģ£
    0.05
    ipe
    0.05
    ater
    0.05
    ÏĢο
    0.05
    æ¹¾
    0.05
    ród
    0.05
    è¿Ļ件äºĭæĥħ
    0.05
    åħľ
    0.05
    æĪ¿çļĦ
    0.05
    ãģ¨ãĤĤ
    0.05
    Activations Density 0.061%

    No Known Activations