© 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. 22266
    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
    ferred
    -0.06
    ุà¸Ķ
    -0.05
    ä¸ĭæĮ«
    -0.05
    ä¸ĸäºĭ
    -0.05
     ready
    -0.05
    gp
    -0.05
     useForm
    -0.05
     маÑģÑĤ
    -0.05
    erring
    -0.05
     chá»Ĺ
    -0.05
    POSITIVE LOGITS
    isky
    0.07
     itself
    0.07
    YYYY
    0.06
    нÑĮÑĤе
    0.06
    SEX
    0.06
    å°±æĺ¯ä¸ª
    0.06
    ileo
    0.06
     complying
    0.06
    ician
    0.06
    ãģıãģł
    0.06
    Activations Density 0.000%

    No Known Activations