© 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. 22174
    Prev
    Next
    INDEX
    Explanations

    resource management

    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
    olls
    -0.06
    inii
    -0.06
    룰
    -0.06
    amatkan
    -0.06
    æīĵæĵĬ
    -0.05
    ÛĮÙħاÙĨ
    -0.05
    大ä¸Ģ
    -0.05
    enger
    -0.05
    czÄĻ
    -0.05
     deter
    -0.05
    POSITIVE LOGITS
    åĪĨéħįçļĦ
    0.06
    æĢ¥äºĨ
    0.06
    istik
    0.05
    大åĪ©
    0.05
    ä½ľæ³ķ
    0.05
     parfaitement
    0.05
     phase
    0.05
     ÑĢаÑģпÑĢеделÑı
    0.05
    å¦
    0.05
    建ç«ĭçļĦ
    0.05
    Activations Density 0.004%

    No Known Activations