© 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. 17985
    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
    åİŁä»¶åıĬ
    -0.06
    estre
    -0.06
    ä»Ģ麼æĻĤåĢĻ
    -0.06
     independ
    -0.06
    è¦ģæ±Ĥè¿Ľè¡Į
    -0.06
    oise
    -0.06
    alet
    -0.06
    æīĢåij¨
    -0.06
    繫
    -0.06
     downstairs
    -0.06
    POSITIVE LOGITS
    ety
    0.07
    å¨ľ
    0.06
    ine
    0.06
    ton
    0.05
    ve
    0.05
    ty
    0.05
    è¾¾
    0.05
    arana
    0.05
    abor
    0.05
    ÑĢи
    0.05
    Activations Density 0.000%

    No Known Activations