© 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. 21490
    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
    ä½ľåĪĻ
    -0.07
    ä¸Ģåıij
    -0.07
    onse
    -0.07
     бÑĢе
    -0.06
     silen
    -0.06
    aire
    -0.06
    raż
    -0.06
    iaires
    -0.06
    aired
    -0.06
    sis
    -0.06
    POSITIVE LOGITS
     ...
    0.05
     rest
    0.05
     pr
    0.05
    4
    0.05
     mem
    0.05
    æĵ
    0.05
    ner
    0.05
    åij½
    0.05
    æijĦ
    0.04
    3
    0.04
    Activations Density 0.000%

    No Known Activations