© 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. 18141
    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
    åĪ©
    -0.06
    èĹı
    -0.05
    enteil
    -0.05
    以ä¸Ĭ
    -0.05
    fl
    -0.05
    æŀ£
    -0.04
     continuation
    -0.04
     sooner
    -0.04
     continu
    -0.04
     longer
    -0.04
    POSITIVE LOGITS
    edet
    0.07
    çģ
    0.06
    adata
    0.06
    lacht
    0.06
    -metadata
    0.06
     Platt
    0.06
    è®
    0.06
    汪æ´ĭ
    0.06
    ноп
    0.06
     تأÙĥ
    0.06
    Activations Density 0.000%

    No Known Activations