© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17805
    Prev
    Next
    INDEX
    Explanations

    json array or object structure

    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
    ewa
    -0.07
    åIJ¬çļĦ
    -0.06
    æĥł
    -0.06
    æŃ¦ä¾¯
    -0.06
    gross
    -0.06
    ç«ŀäºīçļĦ
    -0.06
    aisse
    -0.06
    ç§ĭ鼨
    -0.05
    足çļĦ
    -0.05
    è¨Ģä¹ĭ
    -0.05
    POSITIVE LOGITS
    CP
    0.05
    åīįæľŁ
    0.05
     D
    0.05
    æ»ħ
    0.05
    ikon
    0.05
    ier
    0.05
    ÑĮ
    0.05
    åĬłæ²¹
    0.05
    çļĦ建ç«ĭ
    0.05
     Ùħشخص
    0.05
    Activations Density 0.003%

    No Known Activations