© 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. 19406
    Prev
    Next
    INDEX
    Explanations

    ldap, AD, directory services

    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
     patented
    -0.07
    ienz
    -0.06
    Unnamed
    -0.06
    ä¼ģ稳
    -0.06
    leccion
    -0.06
    ijen
    -0.06
    leger
    -0.06
    iland
    -0.06
     airstrikes
    -0.06
     royalty
    -0.06
    POSITIVE LOGITS
    绣ä¸Ģ
    0.06
    绣ä¸ĢçļĦ
    0.06
    ync
    0.06
    æĺ¥ç§ĭ
    0.06
    è¿ģ移
    0.06
    Sync
    0.06
     central
    0.06
    绣ä¸Ģ管çIJĨ
    0.06
     Uniform
    0.06
    管çIJĨ
    0.05
    Activations Density 0.057%

    No Known Activations