© 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. 19470
    Prev
    Next
    INDEX
    Explanations

    acid 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
    athi
    -0.07
    æľĶ
    -0.06
    hd
    -0.06
    ç½®ä¹ĭ
    -0.06
     sÃłng
    -0.06
    ìķĺëįĺ
    -0.06
    istet
    -0.06
    ocked
    -0.06
    ifer
    -0.06
    jeni
    -0.06
    POSITIVE LOGITS
    ed
    0.06
    æ°´
    0.05
    little
    0.05
    ziale
    0.05
    Ĺ
    0.05
    zah
    0.05
    æĻĹ
    0.05
    íıŃ
    0.05
     little
    0.05
     resil
    0.05
    Activations Density 0.001%

    No Known Activations