© 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. 18986
    Prev
    Next
    INDEX
    Explanations

    real roots of polynomials

    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
     Trabaj
    -0.06
    æŁIJç§į
    -0.05
    esar
    -0.05
    ervo
    -0.05
    éķ¿é£İ
    -0.05
     eventualmente
    -0.05
    ä¸įè¨Ģ
    -0.05
    ieta
    -0.05
    åĭķãģı
    -0.05
    鱿
    -0.05
    POSITIVE LOGITS
     perk
    0.06
     sights
    0.06
    åľ©
    0.05
     Perc
    0.05
    navigator
    0.05
    emaker
    0.05
    tractive
    0.05
    illis
    0.05
    cede
    0.05
    Âł
    0.05
    Activations Density 0.016%

    No Known Activations