© 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. 19669
    Prev
    Next
    INDEX
    Explanations

    verb endings / suffixes

    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
    ä¸Ģä¸Ģ
    -0.06
     way
    -0.06
     means
    -0.05
    elih
    -0.05
    vable
    -0.05
    å¹Į
    -0.05
    åı¸
    -0.05
    ä¸Ģä½ĵ
    -0.05
    uestos
    -0.05
     yanı
    -0.05
    POSITIVE LOGITS
    icer
    0.07
    estr
    0.06
    hur
    0.06
     boul
    0.06
    mist
    0.06
     beker
    0.06
    è¿ĺçĶ¨
    0.06
    iest
    0.06
    eka
    0.05
    ENER
    0.05
    Activations Density 0.091%

    No Known Activations