© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20776
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    èİ·è¯Ħ
    -0.05
     incumb
    -0.05
    rieve
    -0.05
    çĶŁéķ¿åľ¨
    -0.05
    屡
    -0.05
    .double
    -0.05
     Settembre
    -0.05
    ouncement
    -0.05
    寿åİ¿
    -0.05
    èĦĤ
    -0.05
    POSITIVE LOGITS
     recently
    0.06
    abbage
    0.06
     soon
    0.05
     COLL
    0.05
     adore
    0.05
    ariana
    0.05
    æľĢæĸ°çļĦ
    0.05
    åı¯ä»¥çĤ¹åĩ»
    0.05
    oha
    0.05
     collar
    0.05
    Activations Density 0.062%

    No Known Activations