© 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. 18676
    Prev
    Next
    INDEX
    Explanations

    settle in or down

    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
    kaar
    -0.07
     ноÑĩи
    -0.07
    ä½Ļç§į
    -0.07
    еÑĩа
    -0.07
    IFICATIONS
    -0.06
    кала
    -0.06
    erior
    -0.06
    ä½Ļç¯ĩ
    -0.06
    deaux
    -0.06
    kelig
    -0.06
    POSITIVE LOGITS
    çļĦåıĺåĮĸ
    0.06
    ÑĤи
    0.05
    izen
    0.05
    åıĸåIJij
    0.05
    ÙĪاÙĨ
    0.05
    aimer
    0.05
    æ±Łæ¹ĸ
    0.05
    èݽ
    0.05
    æ°ijåĪĿ
    0.05
     dĩ
    0.05
    Activations Density 0.009%

    No Known Activations