© 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. 18775
    Prev
    Next
    INDEX
    Explanations

    field of the invention relates to

    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
    zÄĻ
    -0.05
    -
    -0.05
    inkt
    -0.05
    walten
    -0.05
     ÙħؤÙĥدا
    -0.05
    usel
    -0.05
    overs
    -0.05
    æĶĴ
    -0.04
     Suns
    -0.04
    çļİ
    -0.04
    POSITIVE LOGITS
    ждÑĥÑİ
    0.07
     geler
    0.06
     libertine
    0.06
     webové
    0.06
    ,'\
    0.06
     célé
    0.06
     libertin
    0.05
     istim
    0.05
    bardziej
    0.05
     anzus
    0.05
    Activations Density 0.147%

    No Known Activations