© 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. 20805
    Prev
    Next
    INDEX
    Explanations

    first mention or record

    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
    olon
    -0.05
    é¢
    -0.05
    æŧçļĦ
    -0.05
    家æĶ¿
    -0.05
    ยà¹Īà¸Ńย
    -0.05
    èĩªå°Ĭ
    -0.05
    åIJ¸åıĸ
    -0.05
    å©´
    -0.05
     từng
    -0.05
     Äijạo
    -0.05
    POSITIVE LOGITS
    说ä»ĸ
    0.06
    æıIJåıĬ
    0.06
     Pró
    0.06
     earliest
    0.06
    åľĪåĨħ
    0.06
     unavoid
    0.06
    说她
    0.06
     DESCRIPTION
    0.05
    å°±æĺ¯ä»ĸ
    0.05
    trat
    0.05
    Activations Density 0.087%

    No Known Activations