© 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. 20645
    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
    ä»·
    -0.05
    imer
    -0.05
    éĢĤçĶ¨
    -0.04
    è¦ģä¸į
    -0.04
    cloud
    -0.04
    roy
    -0.04
    edan
    -0.04
    Âł
    -0.04
    å¹´ç§ĭåŃ£
    -0.04
    æĦıè§ģ
    -0.04
    POSITIVE LOGITS
    åį«ä¸ľ
    0.07
    ردة
    0.07
    宿
    0.06
    trap
    0.06
    fold
    0.06
    udas
    0.06
     wards
    0.06
    gli
    0.06
    ected
    0.06
    ded
    0.06
    Activations Density 0.000%

    No Known Activations