© 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. 21212
    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
     ninh
    -0.06
    iger
    -0.06
    IGH
    -0.06
    uwd
    -0.06
     sana
    -0.06
    æ½ľåľ¨çļĦ
    -0.06
    опеÑĢа
    -0.06
    potential
    -0.06
    æ½ľåľ¨
    -0.05
    legen
    -0.05
    POSITIVE LOGITS
    ients
    0.05
    è¡Į
    0.05
    æľ¬èº«
    0.05
    odos
    0.05
    T
    0.05
    åģı
    0.05
    åĪĩ
    0.05
     veille
    0.05
     finally
    0.05
     e
    0.05
    Activations Density 0.000%

    No Known Activations