© 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. 22287
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    符
    -0.07
    éĴ§
    -0.06
    æķĻæĪij
    -0.06
    å®ı
    -0.06
     press
    -0.06
    éªı
    -0.06
    irst
    -0.06
    ancen
    -0.06
    æ¨
    -0.06
    客æĪ·çļĦéľĢæ±Ĥ
    -0.06
    POSITIVE LOGITS
    neh
    0.06
    fol
    0.05
    è¿ijçļĦ
    0.05
    akk
    0.05
    ak
    0.05
    vel
    0.05
    ako
    0.05
    uktur
    0.05
    åı¶éħ¸
    0.05
    大ä¼ļ
    0.05
    Activations Density 0.000%

    No Known Activations