© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19440
    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
    “
    -0.05
    inen
    -0.05
    illen
    -0.05
    rou
    -0.05
    aran
    -0.05
    éļľ
    -0.05
    æ¡ĪçļĦ
    -0.05
    ...
    -0.04
    isen
    -0.04
    ×ķת
    -0.04
    POSITIVE LOGITS
    undur
    0.07
    èī²åĪĹ
    0.07
    ÑĤали
    0.07
    reis
    0.07
    åıijå¸ĥåħ¬åijĬ称
    0.07
    äºĨæĮĩ
    0.07
     perdana
    0.07
     vét
    0.07
     movil
    0.07
     ìĪĺë°ĸìĹIJ
    0.07
    Activations Density 0.000%

    No Known Activations