© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18977
    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
    æľīç¥ŀ
    -0.05
    enames
    -0.05
    нÑı
    -0.05
    kak
    -0.05
    inz
    -0.05
    dom
    -0.05
    adam
    -0.05
    agam
    -0.05
    åħħå®ŀ
    -0.05
    åħħ
    -0.04
    POSITIVE LOGITS
    owel
    0.06
    å®ļæľŁçļĦ
    0.06
    prü
    0.06
     capable
    0.06
    大夫
    0.06
     malos
    0.06
    ç»ĵæŀľæĺ¯
    0.06
    .databinding
    0.06
    ecta
    0.06
    æĹ¥è¶ĭ
    0.05
    Activations Density 0.000%

    No Known Activations