© 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. 19726
    Prev
    Next
    INDEX
    Explanations

    tooth

    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
    riu
    -0.07
    anga
    -0.07
    getOrElse
    -0.07
    ouro
    -0.07
    à¸Ńà¸Ļุà¸įาà¸ķà¹ĥหà¹īà¸Ļำ
    -0.07
    èĻ½çĦ¶åľ¨
    -0.07
    missive
    -0.07
    nacht
    -0.07
    ãĤį
    -0.07
    GGLE
    -0.07
    POSITIVE LOGITS
    0.06
    er
    0.05
     (
    0.05
     +
    0.05
     No
    0.05
    ...
    0.05
     level
    0.05
    +
    0.05
     Core
    0.05
    -level
    0.05
    Activations Density 0.084%

    No Known Activations