© 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. 19711
    Prev
    Next
    INDEX
    Explanations

    personal connection and belonging

    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
    æĬĬä¸Ģ个
    -0.05
    æĢ»éĥ¨
    -0.05
    elf
    -0.05
    å¾Ĵ
    -0.05
    âĢ¦
    -0.05
    §
    -0.05
    loon
    -0.05
    æīį
    -0.05
    olo
    -0.05
    &
    -0.05
    POSITIVE LOGITS
    ccess
    0.06
    CESS
    0.06
     méda
    0.06
    usiasme
    0.06
    cest
    0.06
     инг
    0.06
    meld
    0.06
    оеди
    0.06
    çĪĨäºĨ
    0.06
    raison
    0.06
    Activations Density 0.009%

    No Known Activations