© 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. 19568
    Prev
    Next
    INDEX
    Explanations

    and percentages

    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
    ocene
    -0.06
    سط
    -0.06
    ophil
    -0.06
    ucci
    -0.06
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    lebt
    -0.06
    åİĨ
    -0.05
     envies
    -0.05
    atron
    -0.05
     depended
    -0.05
    POSITIVE LOGITS
    gh
    0.05
     proof
    0.05
     begun
    0.05
    æķ²åĵį
    0.05
     ut
    0.05
    ä½ķä¸į
    0.05
    anh
    0.05
    conta
    0.05
    taa
    0.05
    ép
    0.05
    Activations Density 0.021%

    No Known Activations