© 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. 21609
    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
    诸å¦Ĥ
    -0.08
    走访æħ°éĹ®
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    åľ¨åIJĦç§į
    -0.06
    Nation
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.06
    itorium
    -0.06
     Nation
    -0.06
    头çļĦ
    -0.06
    uas
    -0.06
    POSITIVE LOGITS
    edale
    0.05
    Ñı
    0.05
    opo
    0.05
    æĥľ
    0.05
    èĤ¡
    0.05
    羣çĪ±
    0.05
     equip
    0.05
    ral
    0.05
    æĪijè¡Į
    0.05
     prospect
    0.05
    Activations Density 0.000%

    No Known Activations