© 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. 18395
    Prev
    Next
    INDEX
    Explanations

    what was removed, merged, added, and changed

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     rights
    -0.05
    å¾Ĵ
    -0.05
    æŃĮ
    -0.05
    é£İ
    -0.05
     mechanics
    -0.05
    net
    -0.05
    课æĸĩ
    -0.05
    !
    -0.05
    વા
    -0.05
    ing
    -0.05
    POSITIVE LOGITS
    åĺĪ
    0.07
    ehren
    0.06
    alone
    0.06
    ẹp
    0.06
    ziek
    0.06
    她表示
    0.06
     withd
    0.06
    âĢ¦but
    0.06
    ιδ
    0.06
    adis
    0.06
    Activations Density 0.001%

    No Known Activations