© 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. 19551
    Prev
    Next
    INDEX
    Explanations

    if possible or applicable

    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
     whenever
    -0.06
    åĽłäºº
    -0.06
     wherever
    -0.06
    æŶä¼ļ
    -0.06
     locate
    -0.05
     اÙĦÙĤص
    -0.05
     Dos
    -0.05
    icul
    -0.05
    engesch
    -0.05
    åĴĮæݨ广
    -0.05
    POSITIVE LOGITS
    alti
    0.06
    allet
    0.05
    .communic
    0.05
    áno
    0.05
    çĶŁçĶŁ
    0.05
    bod
    0.05
    äºļ
    0.05
    vad
    0.05
    ectiv
    0.05
     vet
    0.05
    Activations Density 0.006%

    No Known Activations