© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16997
    Prev
    Next
    INDEX
    Explanations

    private

    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
     read
    -0.06
    .integration
    -0.05
    رائ
    -0.05
     integration
    -0.05
    ore
    -0.05
    ores
    -0.05
    awn
    -0.05
    lega
    -0.05
    çıĬçıĬ
    -0.05
    integration
    -0.05
    POSITIVE LOGITS
     Private
    0.05
    /private
    0.05
    çĵ¢
    0.05
    å®ŀéĻħåĩºåıij
    0.05
    aja
    0.05
     recognizable
    0.05
     PRIVATE
    0.05
     private
    0.05
    ender
    0.05
     privadas
    0.05
    Activations Density 0.004%

    No Known Activations