© 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. 19846
    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
    egy
    -0.06
    aky
    -0.06
     profess
    -0.06
    wij
    -0.05
    è¿ľè·Ŀ离
    -0.05
    ãĥĻãĥ³
    -0.05
     sugges
    -0.05
    URRE
    -0.05
     explan
    -0.05
     пÑĢожи
    -0.05
    POSITIVE LOGITS
    isons
    0.06
    mits
    0.06
    ÙĦاØŃ
    0.06
    adders
    0.06
    lement
    0.05
    zp
    0.05
    ä¸Ģåĩº
    0.05
    漫
    0.05
    åIJĮå·¥
    0.05
    ols
    0.05
    Activations Density 0.000%

    No Known Activations