© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20517
    Prev
    Next
    INDEX
    Explanations

    both or paired

    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
    ãi
    -0.05
    å¹´ãģ«ãģ¯
    -0.05
    缮çļĦæĺ¯
    -0.05
    æĶ¹åĪ¶
    -0.05
    lem
    -0.05
    lect
    -0.05
    agen
    -0.05
    .getvalue
    -0.05
     neglect
    -0.05
    egi
    -0.05
    POSITIVE LOGITS
     both
    0.08
     pair
    0.08
     simultaneously
    0.07
     paired
    0.07
    both
    0.07
     BOTH
    0.07
    æĹ¢æĺ¯
    0.07
     pairs
    0.07
    åIJĮæŶ
    0.07
    _both
    0.06
    Activations Density 0.215%

    No Known Activations