© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19757
    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
    L
    -0.06
    æİĮ
    -0.05
    è½°
    -0.05
    ç³»ç»Łä¸ŃçļĦ
    -0.05
    éĩįå¤§é¡¹çĽ®
    -0.05
    illen
    -0.05
    æĿ¿åĿĹ
    -0.05
    1
    -0.05
    åĽŀçŃĶéĹ®é¢ĺ
    -0.05
    ston
    -0.05
    POSITIVE LOGITS
    ensem
    0.07
    Õ¸ÖĤÕ©Õµ
    0.07
    ðŁĺī
    0.06
    abut
    0.06
    ðŁĺĢ
    0.06
    лома
    0.06
    биÑĤе
    0.06
    kira
    0.06
     ðŁĺĢ
    0.06
     kĩ
    0.06
    Activations Density 0.000%

    No Known Activations