© 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. 19563
    Prev
    Next
    INDEX
    Explanations

    ratio, division, difference, between

    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
    Sep
    -0.05
    raje
    -0.05
    hle
    -0.05
    ira
    -0.05
    æķŀ
    -0.05
    IR
    -0.05
     pleas
    -0.05
    _completion
    -0.05
    inga
    -0.05
    istic
    -0.05
    POSITIVE LOGITS
    ark
    0.06
    èµ·çļĦ
    0.06
    rost
    0.05
    å¹³åĿ¦
    0.05
    åıĪæĬĬ
    0.05
    被æµĭ
    0.05
    angan
    0.05
     Nasi
    0.05
    åľ¨è¿ĩåİ»
    0.05
    odcast
    0.05
    Activations Density 0.152%

    No Known Activations