© 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. 20902
    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
     scientif
    -0.07
    emmin
    -0.06
    Ùĥذا
    -0.06
    å¼ĢçªĹ
    -0.06
     wÄħtp
    -0.06
    åħ¶ä»ĸæĸ¹å¼ı
    -0.06
     roup
    -0.06
    ÙĨاÙģ
    -0.06
    دة
    -0.06
    å¾ĢæľŁç²¾å½©
    -0.06
    POSITIVE LOGITS
    ias
    0.06
    åĻ©
    0.05
     alongside
    0.05
    èµĦ产
    0.05
    acr
    0.05
    vented
    0.05
    iated
    0.05
    å¹ħ
    0.05
    ãģ«ãģ¤
    0.05
     ub
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.