© 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. 18820
    Prev
    Next
    INDEX
    Explanations

    adjuvant

    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
    arg
    -0.05
    çij¾
    -0.05
    als
    -0.05
     arg
    -0.05
     firm
    -0.05
    ana
    -0.05
    é£İåħī
    -0.05
     Mandal
    -0.05
    YRO
    -0.05
     NS
    -0.05
    POSITIVE LOGITS
     scientif
    0.06
    acion
    0.05
    édé
    0.05
     plasti
    0.05
     thá»į
    0.05
    긴
    0.05
    漿
    0.05
    untut
    0.05
    kund
    0.05
    IBA
    0.05
    Activations Density 0.001%

    No Known Activations