© 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. 19678
    Prev
    Next
    INDEX
    Explanations

    explicitly about comparison

    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
    cry
    -0.06
     kehil
    -0.06
    celain
    -0.06
    קר
    -0.05
     ë§ŀ
    -0.05
    fcntl
    -0.05
    emean
    -0.05
    >{"
    -0.05
    roperty
    -0.05
    -indent
    -0.05
    POSITIVE LOGITS
    isa
    0.06
    enÃŃ
    0.06
    eks
    0.06
     Hos
    0.06
    ise
    0.06
    eps
    0.06
    eter
    0.06
    ech
    0.05
    ier
    0.05
    gl
    0.05
    Activations Density 0.001%

    No Known Activations