© 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. 19639
    Prev
    Next
    INDEX
    Explanations

    configure preferences

    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
    VO
    -0.06
    éĥ¨åĪĨ
    -0.05
    gon
    -0.05
     Literature
    -0.05
    åıijçĶŁåıĺåĮĸ
    -0.05
    ono
    -0.05
     Prima
    -0.05
    strand
    -0.05
    lore
    -0.05
    çľ¼æ³ª
    -0.05
    POSITIVE LOGITS
    æŃ¥åħ¥
    0.06
    ider
    0.06
    رÙĪع
    0.06
    à¹Ħà¸Ķà¹īà¸Ńย
    0.06
     clad
    0.06
     à¹Ģà¸Ĥà¹īาสูà¹Ī
    0.06
    éĵºå¼Ģ
    0.05
     répart
    0.05
     darin
    0.05
    .eql
    0.05
    Activations Density 0.012%

    No Known Activations