© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19744
    Prev
    Next
    INDEX
    Explanations

    `List<String>`

    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
     himself
    -0.06
    serrat
    -0.06
    为éĺ²æŃ¢
    -0.05
     itself
    -0.05
    ype
    -0.05
     herself
    -0.05
    åĴĮä»ĸçļĦ
    -0.05
    æł·
    -0.05
    ä¹İ
    -0.05
    -like
    -0.05
    POSITIVE LOGITS
    hausen
    0.07
    çİ©åĦ¿
    0.06
    æĸ¯é¡¿
    0.06
     (~(
    0.06
     cóm
    0.06
    ÑĹн
    0.06
    >(_
    0.06
    rani
    0.06
    cing
    0.06
    tiri
    0.05
    Activations Density 0.025%

    No Known Activations