© 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. 18802
    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
    æŃ¤åľ°
    -0.06
    åıĬ以ä¸ĭ
    -0.06
     Nets
    -0.05
    оÑģÑĮ
    -0.05
    åİĺ
    -0.05
    ovali
    -0.05
    ovi
    -0.05
    UND
    -0.05
    Ñĥк
    -0.05
    ovala
    -0.05
    POSITIVE LOGITS
    éĴ§
    0.06
    表éĿ¢ä¸Ĭ
    0.06
    annies
    0.06
    opensource
    0.06
    hall
    0.06
    æĸ¹éĿ¢
    0.05
     chauff
    0.05
    ibri
    0.05
    /errors
    0.05
    রà§į
    0.05
    Activations Density 0.000%

    No Known Activations