© 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. 21914
    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
     sung
    -0.06
    æĢ§è¡Į为
    -0.05
    resta
    -0.05
     ì§ĵ
    -0.05
    òa
    -0.05
    太éĺ³
    -0.05
    ÙĪات
    -0.05
    ника
    -0.05
    egral
    -0.05
    ung
    -0.05
    POSITIVE LOGITS
    chs
    0.06
    0.06
    akas
    0.06
    ÑħÑĢо
    0.06
    пÑĥÑĤ
    0.06
    eland
    0.06
    éķ¿çº¦
    0.06
     Berm
    0.05
    èľ
    0.05
    ege
    0.05
    Activations Density 0.000%

    No Known Activations