© 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. 18956
    Prev
    Next
    INDEX
    Explanations

    published date

    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
    ed
    -0.08
    atika
    -0.06
    ìį¨
    -0.06
    о
    -0.06
    สุà¸Ĥà¸łà¸²à¸ŀ
    -0.06
    onto
    -0.06
    обе
    -0.06
    ÛĮ
    -0.05
    iga
    -0.05
    สà¹Īวà¸Ļ
    -0.05
    POSITIVE LOGITS
    äºĨæĪij们
    0.07
    äºĨä½ł
    0.06
    æĪĸåĪłéĻ¤
    0.06
    äºĨè¿Ļ个
    0.06
    åľ¨åį³
    0.06
    iating
    0.06
    äºĨçļĦ
    0.06
    etti
    0.06
    elli
    0.06
    på
    0.06
    Activations Density 0.051%

    No Known Activations