© 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. 19409
    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
     D
    -0.05
    ri
    -0.05
    ree
    -0.05
    å±Ģ
    -0.05
    j
    -0.05
    è£Ĥ
    -0.05
    IX
    -0.05
    chn
    -0.04
     reserved
    -0.04
    åİ»äºĨ
    -0.04
    POSITIVE LOGITS
    EVER
    0.07
    tris
    0.07
     pepe
    0.07
    oton
    0.06
    åĴĮåIJĮäºĭ
    0.06
    anzas
    0.06
    igur
    0.06
     numberOfRows
    0.06
    åĨįæĿ¥
    0.06
    è¯ı
    0.06
    Activations Density 0.000%

    No Known Activations