© 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. 17960
    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
    ante
    -0.06
    us
    -0.06
    ×ķ×ĸ
    -0.06
    ÙĬÙĩ
    -0.05
     Weiner
    -0.05
    ango
    -0.05
    il
    -0.05
    gh
    -0.05
    RelativeTo
    -0.05
    ç¼
    -0.05
    POSITIVE LOGITS
    зна
    0.06
    ä½Ĩä»įçĦ¶
    0.06
    åĹĵåŃIJ
    0.06
    声
    0.05
    åĹĵ
    0.05
    åĪĩå°Ķ
    0.05
    -serving
    0.05
     séqu
    0.05
     duch
    0.05
    æľºä¼ļ
    0.05
    Activations Density 0.000%

    No Known Activations