© 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. 20375
    Prev
    Next
    INDEX
    Explanations

    adding edges or nodes

    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
    ingen
    -0.07
    à¸Ĭà¸Ļ
    -0.06
    Ñijд
    -0.06
    ambo
    -0.06
    è¿ŀäºij
    -0.06
    onas
    -0.06
    缸åħ³åįķä½į
    -0.06
    Tes
    -0.05
    LER
    -0.05
    oft
    -0.05
    POSITIVE LOGITS
    çĭ¬ç«ĭæĢ§
    0.05
    дÑĢÑĥ
    0.05
    主å¸Ń
    0.05
    Ð¢Ðł
    0.05
     BÃŃ
    0.05
    çĤ¹æѤ
    0.05
     risc
    0.05
    æĦıèŃĺ
    0.05
    æĪıåī§
    0.05
     typography
    0.05
    Activations Density 0.003%

    No Known Activations