© 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. 17652
    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
    иÑĤелÑĮ
    -0.05
     pose
    -0.05
    æĭŁ
    -0.05
    åİ»
    -0.04
    sett
    -0.04
    å°½èģĮ
    -0.04
    åħļ
    -0.04
    éĩĩ
    -0.04
    åĸĦ
    -0.04
    åIJĮ
    -0.04
    POSITIVE LOGITS
    iqué
    0.07
    åħ¬è®¤çļĦ
    0.06
    æĪij社
    0.06
    à¹Ģà¸Ħร
    0.06
    é§ķ
    0.06
     Nhan
    0.06
    eix
    0.06
    æľ¬ç¤¾
    0.06
    æ·±åħ¥æµħ
    0.06
    LABEL
    0.06
    Activations Density 0.000%

    No Known Activations