© 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. 18678
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
     absor
    -0.06
    -0.06
    ائ
    -0.05
    对åIJ§
    -0.05
    ior
    -0.05
    æĪijçľĭ
    -0.05
    天ä¸ĭ第ä¸Ģ
    -0.05
     satunya
    -0.05
    æĪĸèĢħ说
    -0.05
     dobu
    -0.05
    POSITIVE LOGITS
    trys
    0.07
    ekan
    0.06
    ï¼īãĥ»
    0.06
    lets
    0.06
    è´¨çļĦ
    0.06
    åıĬæŶåIJij
    0.06
    resse
    0.06
    sert
    0.06
    reti
    0.06
    Ùĩاب
    0.06
    Activations Density 0.030%

    No Known Activations